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

    Neuronpedia

    INDEX
    Explanations

    words related to physical attributes and appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ùİد
    -0.17
    inks
    -0.16
    ussed
    -0.15
    leys
    -0.15
    ley
    -0.15
    hq
    -0.14
    аÑĨии
    -0.14
    aucoup
    -0.14
    nze
    -0.14
    etics
    -0.13
    POSITIVE LOGITS
    erve
    0.15
    Õ¡
    0.14
    alc
    0.14
    ilip
    0.14
    зÑĥ
    0.14
    ervo
    0.13
    ÑijÑĢ
    0.13
    бо
    0.13
    ORK
    0.13
    afort
    0.13
    Act Density 0.161%

    No Known Activations