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

    Neuronpedia

    INDEX
    Explanations

    terms associated with mathematical or statistical norms and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gba
    -0.18
    ULA
    -0.17
    aders
    -0.15
    digit
    -0.14
    éļ
    -0.14
    umar
    -0.14
    vla
    -0.14
    ula
    -0.14
    anean
    -0.14
    ancode
    -0.14
    POSITIVE LOGITS
    ÙĪبÛĮ
    0.16
     Harley
    0.16
    ãĥ¼ãĥª
    0.15
    zs
    0.15
    957
    0.14
     Gest
    0.14
    -slide
    0.14
     Viet
    0.14
    ilen
    0.13
    otch
    0.13
    Act Density 0.001%

    No Known Activations