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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating doubt, uncertainty, or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.78
    principalColumn
    -0.70
     ApiException
    -0.64
     beginnetje
    -0.64
     nationales
    -0.61
     nahilalakip
    -0.56
    XmlAccessType
    -0.55
    parsedMessage
    -0.54
     Majefty
    -0.54
    numerusform
    -0.53
    POSITIVE LOGITS
    是不是
    0.56
     maybe
    0.56
     benar
    0.55
     either
    0.54
    是否有
    0.54
     suspect
    0.53
     Maybe
    0.53
    thâu
    0.51
     nějak
    0.51
    Vielleicht
    0.50
    Act Density 0.753%

    No Known Activations