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

    Neuronpedia

    INDEX
    Explanations

    references to significant examples or cases within a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UGE
    -0.15
    hausen
    -0.15
    /MPL
    -0.14
    olon
    -0.14
    ноп
    -0.14
    anton
    -0.14
    anca
    -0.14
    ocha
    -0.13
     itemprop
    -0.13
    aos
    -0.13
    POSITIVE LOGITS
     example
    0.16
     пÑĢимеÑĢ
    0.15
    uar
    0.15
    orest
    0.15
    rar
    0.14
     suche
    0.14
     partial
    0.14
     ÙħÙĨÙĩا
    0.14
    otal
    0.14
    lectual
    0.13
    Act Density 0.282%

    No Known Activations