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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific programming terms and conditional constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plain
    -0.17
    swick
    -0.16
    vale
    -0.16
    efeller
    -0.16
    workers
    -0.15
    toi
    -0.15
    ëį°ìĿ´íĬ¸
    -0.15
    uality
    -0.14
    thora
    -0.14
    elmet
    -0.14
    POSITIVE LOGITS
    ness
    0.25
    NESS
    0.20
    naments
    0.20
    -called
    0.18
    /from
    0.18
    most
    0.18
    plevel
    0.18
    Ù
    0.17
    nown
    0.17
    /out
    0.17
    Act Density 0.437%

    No Known Activations