Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to quantitative evaluations or scoring metrics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    score and scoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mian
    -0.46
    pacific
    -0.45
     Hab
    -0.43
     new
    -0.42
    new
    -0.41
    principal
    -0.41
     Chapman
    -0.40
    PlainText
    -0.40
     Tode
    -0.40
     plan
    -0.40
    POSITIVE LOGITS
     scored
    1.05
     score
    1.01
     Score
    0.90
     scoring
    0.86
    scored
    0.84
     SCORE
    0.81
     Scoring
    0.79
     scorer
    0.78
     puntuación
    0.77
    scoring
    0.76
    Act Density 0.016%

    No Known Activations