factual
LLM layers predict brain activity above chance
Representational similarity analysis shows that LLM layer activations predict human brain activation patterns in vision, audio, and language above chance levels, and larger, more capable models correspond more closely to the human brain.
factualpending
Speaker
Chandra SripadaEvidence Quote
“And there's now this entire body of results saying in vision, in auditory processing, in language processing, yeah, you're getting these correspondences.”
Created: 11/17/2026, 6:53:48 AM
Your notes
Loading notes...