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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Who
    -0.58
     जो
    -0.49
    ضا
    -0.49
    waa
    -0.47
    MessageId
    -0.46
     яка
    -0.46
    Tikang
    -0.46
     That
    -0.46
     THAT
    -0.46
    ascii
    -0.46
    POSITIVE LOGITS
     whom
    2.12
    whom
    1.85
     Whom
    1.49
    Whom
    1.41
     whome
    0.76
    Datuak
    0.76
    ViewFeatures
    0.75
     RemoteException
    0.71
    CURS
    0.69
     Мексичка
    0.69
    Act Density 0.033%

    No Known Activations