Anthropic researchers use interpretability methods to study Claude's internal workings, finding its selfhood is shaped by both neurons and narratives like human minds.
About Anthropic · DeepMind · OpenAI · Chris Olah · Dario Amodei · Claude Filed #ai-research #artificial-intelligence #interpretability #startups #technology-culture Related God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniques The article surveys mechanistic interpretability methods—linear probes, sparse autoencoders, activation verbalizers, emotion probes, Jacobians—and discusses their strengths, limitations, and recent setbacks in real language models.
also on Chris Olah , #ai-research , Claude , Anthropic 
What Is Claude? Anthropic Doesn’t Know, Either