Circuit Tracer
Anthropic's open tools to see how AI thinks
512 followers
Anthropic's open tools to see how AI thinks
512 followers
Anthropic's open-source Circuit Tracer helps researchers understand LLMs by visualizing internal computations as attribution graphs. Explore on Neuronpedia or use the library. Aims for AI transparency.
🧠🔍 Circuit Tracer by Anthropic is live! Open tools that let you peek inside how AI thinks — transparency just got visual 🤯🛠️
This is really cool and insightful! 👏
So interesting.
Great job, congrats on the launch! 🚀