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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant financial transactions or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //
    -0.79
     sus
    -0.77
    </i>
    -0.67
    :
    -0.65
    ']):
    -0.65
     for
    -0.65
     in
    -0.65
     je
    -0.64
     las
    -0.64
    ing
    -0.64
    POSITIVE LOGITS
    amaño
    0.96
    󠁣
    0.93
     photolibrary
    0.93
    0
    0.91
    GenerationType
    0.91
     مشين
    0.90
    AddTagHelper
    0.89
     myſelf
    0.88
     $_"
    0.88
    ^(@)
    0.87
    Act Density 0.019%

    No Known Activations