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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation that indicate structure or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uktur
    -0.16
    ewis
    -0.16
     porr
    -0.15
    ÙħÙĪÙĦ
    -0.15
    -www
    -0.15
    iversit
    -0.15
    ÙĪاÙĨ
    -0.15
    arı
    -0.14
    untas
    -0.14
    _tC
    -0.14
    POSITIVE LOGITS
    西çľģ
    0.16
     Wing
    0.15
    eton
    0.15
    OrElse
    0.15
    ynamo
    0.15
    .syn
    0.14
    elden
    0.14
    amus
    0.14
    /tags
    0.14
    ãĤ¸ãĤ¢
    0.14
    Act Density 0.001%

    No Known Activations