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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases indicating contrast or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.66
     Wikimedijinoj
    -0.64
    <?
    -0.64
    TagMode
    -0.60
    Données
    -0.59
     snippetHide
    -0.57
    vity
    -0.56
    териалы
    -0.56
     فريبيس
    -0.54
    Rohy
    -0.52
    POSITIVE LOGITS
     honestly
    0.89
     I
    0.88
     hey
    0.85
     maybe
    0.82
     then
    0.82
     tbh
    0.80
     even
    0.76
    honestly
    0.72
     frankly
    0.71
     admittedly
    0.71
    Act Density 0.168%

    No Known Activations