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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "fake."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atto
    -0.18
    aidu
    -0.17
    ache
    -0.15
    phan
    -0.15
    ions
    -0.15
    ÄĽtÅ¡
    -0.15
    udiante
    -0.14
     поÑģл
    -0.14
    ÏĦοκ
    -0.14
    atori
    -0.14
    POSITIVE LOGITS
    kus
    0.16
    anton
    0.16
    -script
    0.14
    olina
    0.14
    ko
    0.14
    _Cmd
    0.14
     scoop
    0.13
    åĨĴ
    0.13
     Bid
    0.13
    KO
    0.13
    Act Density 0.012%

    No Known Activations