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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing disbelief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =>
    -0.69
    EndInit
    -0.65
     CanadaChoose
    -0.65
    OIR
    -0.64
     Wikimedijinoj
    -0.64
    IsContent
    -0.64
    ApiModel
    -0.63
    '],
    -0.60
    !("{}",
    -0.59
     aDecoder
    -0.58
    POSITIVE LOGITS
    存于互联网档案馆
    0.59
    batore
    0.59
     mourut
    0.55
     caroten
    0.54
     rêver
    0.53
    WAUKEE
    0.53
    locaust
    0.52
     avancé
    0.52
    phosa
    0.52
     états
    0.51
    Act Density 0.086%

    No Known Activations