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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </blockquote>
    -0.79
     "
    -0.79
     ?
    -0.71
    ):=\
    -0.69
     des
    -0.69
     <?
    -0.69
     qui
    -0.69
     um
    -0.69
     ist
    -0.68
     est
    -0.68
    POSITIVE LOGITS
     Negroes
    1.00
     AppColors
    1.00
     Swedes
    0.93
     shewn
    0.86
     Majefty
    0.85
     Jesuits
    0.85
     Italij
    0.82
     wrists
    0.81
     barbati
    0.81
    .”)
    0.81
    Act Density 0.056%

    No Known Activations