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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions that communicate opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.67
    parsedMessage
    -0.63
    __*/
    -0.63
    hoeddwyd
    -0.61
    migrationBuilder
    -0.61
     ویکی‌پدی
    -0.60
    ftagPool
    -0.55
     propOrder
    -0.54
     للاسماء
    -0.54
    addContainerGap
    -0.53
    POSITIVE LOGITS
    LikeLike
    0.41
     vorsichtig
    0.35
     needlessly
    0.34
    Cordialement
    0.33
    Porque
    0.33
     mencion
    0.33
     flag
    0.32
     MessageBoxIcon
    0.32
     because
    0.32
    あく
    0.32
    Act Density 0.439%

    No Known Activations