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

    Neuronpedia

    INDEX
    Explanations

    terms related to maximum capacity or extreme conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nile
    -0.17
    iaux
    -0.16
    ger
    -0.15
    alten
    -0.15
    yleft
    -0.14
    urnal
    -0.14
    алов
    -0.14
    leased
    -0.14
    -caption
    -0.14
    817
    -0.14
    POSITIVE LOGITS
    ith
    0.16
    rish
    0.14
    éħĴ
    0.14
    änge
    0.14
    ardu
    0.14
    vero
    0.14
    avan
    0.14
    ĥ
    0.13
    ť
    0.13
    idebar
    0.13
    Act Density 0.007%

    No Known Activations