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

    Neuronpedia

    INDEX
    Explanations

    statements and phrases that indicate relationships, comparisons, and outcomes in discussions or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.86
    MENAFN
    -0.68
     Paglinawan
    -0.68
    NewUrlParser
    -0.67
    MessageOf
    -0.66
    AntiForgeryToken
    -0.66
    Naissance
    -0.66
    windowFixed
    -0.66
    ьаж
    -0.65
     CURIAM
    -0.65
    POSITIVE LOGITS
    🏼
    0.50
     isso
    0.49
    这种情况
    0.49
     kind
    0.48
    msgTypes
    0.47
     الحره
    0.47
    这种
    0.47
    这就是
    0.46
     مشين
    0.45
    ness
    0.45
    Act Density 1.000%

    No Known Activations