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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific characters and symbols in code or text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rende
    -0.16
    ophon
    -0.15
    íĺľ
    -0.14
    .variant
    -0.14
     Reyn
    -0.14
    ÑĩеÑĢ
    -0.14
    stav
    -0.14
    leness
    -0.13
    pen
    -0.13
    ewater
    -0.13
    POSITIVE LOGITS
    olt
    0.18
    enses
    0.15
    ture
    0.15
    oli
    0.15
    ÑĪÑĤов
    0.15
    ää
    0.14
    hibited
    0.14
     Mil
    0.14
    FO
    0.13
    ocaly
    0.13
    Act Density 0.096%

    No Known Activations