[KongchangAI]
Unverified50% confidenceFactExact time

Matched intervention experiments show that perturbing the answer subspace significantly changes model predictions, whereas perturbing the disagreement representation (even with the same dimensions) barely changes predictions, with an effect similar to a random subspace.

1
Sources
50%
Confidence
Long-term
Relevance
11/18/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1182934
API
curl https://kongchang.com/api/v1/knowledge/claims/1182934
MCP
get_claim(id=1182934)