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

    Neuronpedia

    INDEX
    Explanations

    terms related to hypothetical scenarios and academic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.75
     كومونز
    -0.62
     wireType
    -0.58
    مصادر
    -0.55
    KommentareTeilen
    -0.52
     Roper
    -0.51
     Paglinawan
    -0.51
     Smarty
    -0.50
    DropTable
    -0.50
    TypedDataSet
    -0.50
    POSITIVE LOGITS
    tics
    0.90
    tically
    0.86
    tical
    0.80
    tic
    0.78
    tica
    0.70
    ticos
    0.70
    tico
    0.68
    틱
    0.68
    ticism
    0.68
    tik
    0.67
    Act Density 0.239%

    No Known Activations