Phi Score (Extreme Steering Score)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Phi-4concept0.753
  Backbone model used in E3 robustness overlay.
• Criterion 2: Statistically significant Φ value differences (p<0.05) across ToM score categories via Wilcoxon test.concept0.704
  Second of three operational criteria; requires distributional significance in IIT estimates across performance levels.
• Probe scoreconcept0.703
  Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
• gemma-3-1b-it yields only one valid MDS injection score (phi_1,A,up = 4.8) and is excluded from main analysesfinding0.694
  Identified exception to overall MDS effectiveness; reason remains unexplained as a limitation
• Criterion 1: Φ estimates must yield >80% 'good' cases (higher score → higher Φ) per ToM task to indicate potential consciousness.concept0.689
  First of three operational criteria for identifying consciousness phenomena in LLM representations.
• All-token steeringmethod0.689
  Baseline steering method that applies intervention at every token generation step, shown to degrade performance at high strengths
• safety scoresconcept0.681
  Metrics derived from benchmarks to quantify how safe a model is, e.g., refusal rate to harmful requests.
• Models produce first-attempt mean scores 87.8-91.8/100 without steering across all model familiesfinding0.680
  Establishes high baseline quality confirming steering-induced degradation is the experimental signal