[KongchangAI]
Unverified50% confidenceFactExact time

Anthropic的机械可解释性(Mechanistic Interpretability)研究试图在神经网络激活层面定位特定知识的存储位置

1
Sources
50%
Confidence
Long-term
Relevance
7/8/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/210387
API
curl https://kongchang.com/api/v1/knowledge/claims/210387
MCP
get_claim(id=210387)