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

    Neuronpedia

    INDEX
    Explanations

    the presence of parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auc
    -0.19
    pletion
    -0.15
    imens
    -0.14
     thì
    -0.14
    apia
    -0.14
    hiba
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
     however
    -0.14
    SSION
    -0.14
    ppard
    -0.14
    POSITIVE LOGITS
    aka
    0.17
     Levy
    0.14
    antz
    0.13
    arak
    0.13
    ...)↵
    0.13
     Tyto
    0.13
    LEV
    0.13
    ÛĮÙĨÙĩ
    0.13
     Carlton
    0.13
    λει
    0.13
    Act Density 0.421%

    No Known Activations