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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional or uncertain language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gratuites
    -0.55
     étanche
    -0.55
    WriteTagHelper
    -0.53
     donc
    -0.52
     kolei
    -0.51
     ritorno
    -0.51
     fermée
    -0.50
     namelijk
    -0.50
    coledì
    -0.49
     imóvel
    -0.49
    POSITIVE LOGITS
    )‏
    0.69
    though
    0.69
    ांकि
    0.67
    aunque
    0.65
    rawQuery
    0.62
     admittedly
    0.60
    例句
    0.59
    MethodManager
    0.59
    ]--;
    0.58
    Though
    0.58
    Act Density 0.150%

    No Known Activations