Embedding-based Construct Logistic Classifier

Logistic regressor on Qwen3Embedding-0.6B embeddings trained on construct statements; used to measure construct presence in alpha sweeps

Neighborhood — ranked by edge-count

paper

framework

Psychological Steering Framework
uses
The paper's primary contribution: performs unbounded, fluency-constrained sweeps in semantically calibrated centroid units using psychological artifacts

finding

method

Unbounded Alpha Sweep
uses
Procedure sweeping injection coefficient alpha in integer centroid-unit steps with early stopping on nonfluency to find optimal settings

cosine ≥ 0.65 · no typed edge

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

Vector Embedding Representationconcept0.708
The specific type of representation studied in the paper: function f: X→R^n assigning feature vectors to inputs
LLM Binary Experience Classifiermethod0.705
Automated classifier returning binary 0/1 for presence of subjective experience report in model outputs
Logistic surrogate fittingmethod0.704
Fitting a logistic function to success probability as a function of S or shot count to estimate midpoints and widths.
logistic surrogate modelmethod0.701
Sigmoid fit linking S to success probability.
The logistic surrogate is a phenomenological fit, not a mechanistic derivationclaim0.694
Caveat about the threshold analysis
Constitutional Classifiersmethod0.691
Anthropic's inference-time guardrail filtering outputs violating constitutional rules; proposed for CCAI implementation
Input Embedding Similarity Baselinemethod0.688
Baseline method for instruction discovery using surface-level input embedding similarity instead of steering vectors.
Mutual Embeddingconcept0.688
A reinforcing interlock between different materials, mentioned alongside Deep Interlock in West Dean construction.