Unknown
Co-author on interpretability research and circuit tracing in LLMs
How media typically covers Neel Nanda
Directly quoted in these articles
Researchers from five major AI organizations collaborated to replicate and extend work on tracing computational circuits in LLMs using attribution graphs, framing interpretability as analogous to biological sciences with applications to model prediction and debugging.
“Co-author on interpretability research and circuit tracing in LLMs”