Interpreting Large Language Models to Interpret the Brain

Explore groundbreaking research in a lecture from UC San Francisco's Shailee Jain examining the intersection of Large Language Models (LLMs), cognitive science, linguistics, and neuroscience, delving into innovative approaches for understanding both artificial and biological neural networks. Learn how researchers are leveraging insights from LLM interpretation techniques to better comprehend brain function and cognitive processes, while discovering parallel patterns between artificial and natural language processing systems.