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

    Neuronpedia

    INDEX
    Explanations

    instances of function definitions and parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.18
    olumn
    -0.18
    Ïĩαν
    -0.16
    engkap
    -0.15
    xffffffff
    -0.15
    $MESS
    -0.15
    çļĦæĺ¯
    -0.15
    ekim
    -0.15
    ritten
    -0.15
    ãĥ¼ãĥŀ
    -0.14
    POSITIVE LOGITS
    s
    0.17
    ones
    0.17
    rush
    0.16
    ses
    0.15
    atab
    0.15
    ONES
    0.15
    tras
    0.14
    implify
    0.14
    pa
    0.13
     Horton
    0.13
    Act Density 0.120%

    No Known Activations