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

    Neuronpedia

    INDEX
    Explanations

    references to "terms" and discussions related to definitions or conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    him
    -0.17
    身ä¸Ĭ
    -0.16
    xt
    -0.15
    hydr
    -0.15
    aneous
    -0.14
    hy
    -0.14
    iations
    -0.14
    iated
    -0.14
     Placeholder
    -0.14
     $?
    -0.14
    POSITIVE LOGITS
     of
    0.22
    İ
    0.17
     sheer
    0.17
    ontent
    0.16
    Як
    0.16
    doll
    0.15
    quat
    0.15
    keit
    0.15
    ugas
    0.15
     likes
    0.15
    Act Density 0.010%

    No Known Activations