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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sık
    -0.46
     sentirse
    -0.41
    <bos>
    -0.40
    Ten
    -0.39
    起
    -0.39
    </h1>
    -0.36
    devServer
    -0.36
     pār
    -0.36
     presos
    -0.36
    .
    -0.35
    POSITIVE LOGITS
     ویکی‌پدیای
    0.79
     autorytatywna
    0.78
    脚注の使い方
    0.77
    WebElementEntity
    0.76
    SharedDtor
    0.75
     AttributeSet
    0.74
    ISupport
    0.73
     StringTokenizer
    0.71
     дописавши
    0.71
     كومونز
    0.71
    Act Density 0.065%

    No Known Activations