Normalized Area Under Anchoring Trajectory (AUS_N)

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

• Normalized area under S (AUSN)concept0.830
  Average of per-layer S(ℓ) scores, summarizing the breadth of anchoring trajectory.
• normalized area AUSNconcept0.822
  Average of S(ℓ) across layers.
• normalized area under S-curve AUSNconcept0.808
  Average S(ℓ) across layers; another geometry summary.
• Hypothesis: Peak alignment location S_max and normalized trajectory area AUS_N predict shot midpoints θ50hypothesis0.783
  E3 prediction that internal geometry provides a bridge to behavioral thresholds
• Peak anchoring Sbmax and normalized area AUSN correlate with per-item success and internal shot midpoints θ50, providing a geometry-to-behavior bridge.claim0.781
  Main interpretation of E3.
• Layer-wise anchoring trajectoryconcept0.747
  Plot of per-layer anchoring score S(ℓ) across model depth, revealing early dip, mid-layer peak, late standardization.
• The anchoring score S is a predictive correlate of when anchoring succeeds and why small prompt changes yield threshold-like shifts.claim0.721
  A central claim about the operational value of S.
• Concept steering with target vs off-target probe area metric reveals three operational regimes (selectively steerable, encoded but entangled, non-encoded) across SleepFM, REVE, LaBraM.finding0.718
  Result categorizing concept steerability into three distinct regimes.