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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals named "Mark" and variations of that name in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    simpleType
    -0.68
     Winaray
    -0.53
     دیکھیے
    -0.52
    войства
    -0.51
    ویل
    -0.51
    aleigh
    -0.51
    yntaxException
    -0.49
    glDisable
    -0.49
    uete
    -0.48
    стоинства
    -0.48
    POSITIVE LOGITS
     Marks
    1.11
     marks
    1.02
    Marks
    1.00
    marks
    0.95
     MARKS
    0.94
     MARK
    0.92
     Mark
    0.92
     Twain
    0.90
    manship
    0.89
    Mark
    0.88
    Act Density 0.146%

    No Known Activations