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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or quantity, especially in the context of new developments or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardy
    -0.16
    ÑĨо
    -0.15
    enga
    -0.14
    odore
    -0.14
    atis
    -0.14
    ogan
    -0.14
    an
    -0.14
    alez
    -0.14
     Daha
    -0.13
    chw
    -0.13
    POSITIVE LOGITS
    UFFIX
    0.16
    ÃŃsticas
    0.14
    752
    0.14
     Mood
    0.14
    umat
    0.13
    gle
    0.13
    ẩm
    0.13
    аÑĤов
    0.13
    /down
    0.13
    entifier
    0.13
    Act Density 0.273%

    No Known Activations