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

    Neuronpedia

    INDEX
    Explanations

    adjectives that express positive or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.56
    stylers
    -0.55
    ?
    -0.55
    underbrace
    -0.48
    taan
    -0.48
     incidente
    -0.48
     eventualmente
    -0.47
     zak
    -0.47
    卿
    -0.47
     pra
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیای
    0.86
     itſelf
    0.83
    CppMethod
    0.78
    styleType
    0.76
    </thead>
    0.76
    ^(@)
    0.75
     faſt
    0.74
    -------------</
    0.71
     ་་
    0.69
    ."));
    0.68
    Act Density 0.473%

    No Known Activations