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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or specific formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recibirá
    -0.51
    inib
    -0.50
    in
    -0.49
     при
    -0.48
     vicepresidente
    -0.48
    </table>
    -0.47
     Health
    -0.45
    at
    -0.45
     papild
    -0.44
     Información
    -0.44
    POSITIVE LOGITS
     Мексичка
    0.98
     kasarigan
    0.98
     etc
    0.93
     समीक्षक
    0.91
    PyExc
    0.89
    etc
    0.82
     Efq
    0.78
    بوابة
    0.76
    principalTable
    0.75
     Etc
    0.74
    Act Density 0.367%

    No Known Activations