AtP*: An efficient and scalable method for localizing LLM behaviour to components
Paper
•
2403.00745
•
Published
•
12
Neel Nanda
NeelNanda
AI & ML interests
Mechanistic Interpretability
Recent Activity
authored
a paper
about 1 month ago
Do I Know This Entity? Knowledge Awareness and Hallucinations in
Language Models
Organizations
None yet