Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models

Researchers are striving to reverse-engineer artificial intelligence and scan the ‘brains’ of LLMs to see what they are doing, how and why.
  1. Matthew Hutson

    1. Matthew Hutson is a science writer based in New York City.

    View author publications

    You can also search for this author in PubMed  Google Scholar

Cartoon of a large brain-shaped machine made of many computer parts being examined by two puzzled researchers.

Illustration: Fabio Buonocore

David Bau is very familiar with the idea that computer systems are becoming so complicated it’s hard to keep track of how they operate. “I spent 20 years as a software engineer, working on really complex systems. And there’s always this problem,” says Bau, a computer scientist at Northeastern University in Boston, Massachusetts.

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Nature 629, 986-988 (2024)

doi: https://doi.org/10.1038/d41586-024-01314-y

Updates & Corrections

  • Correction 17 May 2024: An earlier version of this article contained an error in the box ‘False logic’. The explanation for the correct answer should have said B.

References

  1. Grosse, R. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2308.03296 (2023).

  2. Li, K. et al. in Proc. Int. Conf. Learn. Represent. 2023 (ICLR, 2023); available at https://openreview.net/forum?id=DeG07_TcZvT

  3. Hagendorff, T. Preprint at arXiv https://doi.org/10.48550/arXiv.2303.13988 (2023).

  4. Wei, J. et al. in Adv. Neural Inf. Process. Syst. 35 (eds Koyejo, S. et al.) 24824–24837 (Curran Associates, 2022); available at https://go.nature.com/3us888x

  5. Turpin, M., Michael, J., Perez, E. & Bowman, S. R. Preprint at arXiv https://doi.org/10.48550/arXiv.2305.04388 (2023).

  6. Zou, A. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2310.01405 (2023).

  7. Meng, K., Sharma, A. S., Andonian, A. J., Belinkov, Y. & Bau, D. in Proc. Int. Conf. Learn. Represent. 2023 (ICLR, 2023); available at https://openreview.net/forum?id=MkbcAHIYgyS

  8. Hase, P., Bansal, M., Kim, B. & Ghandeharioun, A. Preprint at arXiv https://doi.org/10.48550/arXiv.2301.04213 (2023).

Download references

Subjects

Latest on:

Nature Careers

Jobs

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing

Search

Advanced search

Quick links