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

    Neuronpedia

    INDEX
    Explanations

    references to publication details and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĢά
    -0.17
    inding
    -0.15
    echa
    -0.14
    anno
    -0.14
     Morrow
    -0.13
    ark
    -0.13
    H
    -0.13
    ÑĢоÑĩ
    -0.13
    maz
    -0.13
     gó
    -0.13
    POSITIVE LOGITS
    asio
    0.16
    ÙİÙĪ
    0.16
    alon
    0.15
    UTTON
    0.14
    ª
    0.14
    gii
    0.14
    ниÑĨÑĭ
    0.14
    SWG
    0.14
    quirrel
    0.14
    _EXTENSIONS
    0.14
    Act Density 0.151%

    No Known Activations