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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or statistical representations

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

    following numbers or letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -1.02
    ConstraintMaker
    -0.93
     ModelExpression
    -0.88
    principalColumn
    -0.86
    PreInfinity
    -0.82
    MessageTagHelper
    -0.82
    oredCriteria
    -0.81
    LookAnd
    -0.81
    Personendaten
    -0.77
    évaluateur
    -0.76
    POSITIVE LOGITS
     step
    0.43
     steps
    0.43
    step
    0.42
    Step
    0.40
    steps
    0.36
     Step
    0.35
    Steps
    0.35
    STEP
    0.33
     first
    0.31
     Steps
    0.31
    Act Density 0.002%

    No Known Activations