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

    Neuronpedia

    INDEX
    Explanations

    references to variables or instance methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovy
    -0.16
    ddy
    -0.16
     __("
    -0.16
    baugh
    -0.15
    opsy
    -0.14
    ź
    -0.14
    ssc
    -0.14
    ÑĪÑĤов
    -0.14
     Canter
    -0.14
    /octet
    -0.14
    POSITIVE LOGITS
    oton
    0.18
     Rad
    0.16
     peculiar
    0.15
     RAD
    0.15
     novel
    0.15
    otron
    0.14
    sur
    0.14
    rophe
    0.14
    iz
    0.14
    is
    0.14
    Act Density 0.002%

    No Known Activations