method
active
method:l2zi-injectionL2ZI Injection
Probe-based injection using L2-regularized logistic regressor with zero intercept on h_b activations
Neighborhood — ranked by edge-count
Methods (2)
method
- L2LI Injectionrelated_toProbe-based injection using L2-regularized logistic regressor with learned intercept on h_b activations
- L1ZI Injectionrelated_toProbe-based injection using L1-regularized logistic regressor with zero intercept on h_b activations
Related by similarity (5)
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.
- Probe-based injection using L1-regularized logistic regressor with learned intercept on h_b activations
- Parameter controlling how often an injection is applied during completion; s=1 injects on every activation, achieving strongest steering
- Mean-difference vectors derived from self-statement activations (h_s); best-performing injection method in open-ended generation
- Mean-difference vectors derived from Yes/No binary-prefill activations (h_b)
- Technique of injecting activation patterns associated with specific concepts into a model's internal states to test whether self-reports reflect ground truth.