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

    Neuronpedia

    INDEX
    Explanations

    arguments and claims related to evidence and reasoning in discussions

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

    Preceding words implying subjectivity or judgement

    np_acts-logits-general · gemini-2.0-flash

    evaluations of impropriety or unreasonableness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.86
    RTLR
    -0.84
    -0.79
     дописавши
    -0.78
    GraphicsUnit
    -0.74
    Diwedd
    -0.74
    MigrationBuilder
    -0.73
    rrggbb
    -0.71
    tagHelperRunner
    -0.67
     onAnimation
    -0.66
    POSITIVE LOGITS
     bal
    0.48
    ದು
    0.47
    odd
    0.46
    கம்
    0.46
     minor
    0.43
    usia
    0.42
    DRA
    0.41
    Bal
    0.41
     argument
    0.40
     Bal
    0.40
    Act Density 0.328%

    No Known Activations