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

    Neuronpedia

    INDEX
    Explanations

    celebratory expressions or greetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILA
    -0.16
    anh
    -0.15
    anas
    -0.15
    ạt
    -0.15
    ردÙĩ
    -0.14
    illa
    -0.14
    elry
    -0.14
    latable
    -0.14
    /popper
    -0.14
    à¸¸à¸Ľ
    -0.14
    POSITIVE LOGITS
    riel
    0.18
    oria
    0.17
    contri
    0.16
    les
    0.15
    ften
    0.15
    lamaz
    0.15
     ours
    0.15
    ůl
    0.15
    allon
    0.14
    icros
    0.14
    Act Density 0.007%

    No Known Activations