method
active
method:probe-or-monitor-combinationProbe OR Monitor combination
Joint firing raises TPR at slightly higher FPR.
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
- Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
- Synchronization construct encapsulating shared data and protected access routines.
- Joint use improves TPR.
- Reward probe grading correction interventions (5-class).
- Standard interpretability technique used to read feature beliefs.
- Internals-based approach to which the logit monitor is complementary.
- Causal transformer probe predicting whether a token is in the same Entity as its predecessor.