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

    Neuronpedia

    INDEX
    Explanations

    terms related to subcategories and classifications in a hierarchical or structural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ
    -0.17
    vidia
    -0.15
     dol
    -0.14
    icias
    -0.14
    heets
    -0.14
    .Keys
    -0.13
    lier
    -0.13
    ìĨ¡
    -0.13
    advance
    -0.13
     laid
    -0.13
    POSITIVE LOGITS
    (Sub
    0.29
    /Sub
    0.28
    =sub
    0.22
    /sub
    0.21
    (sub
    0.19
    .Sub
    0.18
    [sub
    0.18
     sub
    0.16
    DataExchange
    0.15
    ongyang
    0.15
    Act Density 0.044%

    No Known Activations