method
active
method:mixed-logistic-regression-emotion-probeMixed logistic regression emotion probe
15-way classifier of emotion over five dialogue conditions.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Logistic Regression Proberelated_toStandard linear probing technique; compared to mass-mean probing for classification accuracy and causal implication
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.
- Logistic regression trained on GSM8k training set to predict answer correctness from projection features along reflection direction
- Linear probes constructed to measure 171 emotion concepts in model activations with surface semantic content removed
- Used to test linear separability of group position.
- Method for building 171 emotion probes by generating stories, embedding them, regressing out Gemini embeddings, and averaging residual activations per emotion
- Used to characterize counting representations.
- Emotion probes could serve as real-time monitors that trigger safety measures when desperation or anger spikehypothesis0.746Proposed application.
- Linear representations of emotion concepts extracted from activations.
- Orthogonalizes the 171 emotion probes via SVD to create an orthonormal basis for computing SAE feature subspace overlap