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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating results, benefits, or actions to be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULK
    -0.15
    اÛĮاÙĨ
    -0.15
    outes
    -0.14
    xAB
    -0.14
     shadow
    -0.14
    ạ
    -0.14
    ær
    -0.14
    oker
    -0.14
     shadows
    -0.14
    wart
    -0.14
    POSITIVE LOGITS
    324
    0.17
    olet
    0.16
    fal
    0.15
    clas
    0.15
    loh
    0.14
    apol
    0.14
    ugi
    0.14
    159
    0.14
    .blob
    0.14
    ISCO
    0.14
    Act Density 0.087%

    No Known Activations