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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures or patterns in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.14
    a
    -0.10
    e
    -0.09
    i
    -0.09
    an
    -0.09
    erot
    -0.07
    ed
    -0.07
    ÛĮ
    -0.07
    o
    -0.07
    al
    -0.07
    POSITIVE LOGITS
    _ASSUME
    0.07
     hâl
    0.07
    gree
    0.07
    //(
    0.07
    озможно
    0.07
    éri
    0.07
    IDEOS
    0.07
    ceso
    0.07
    vÃŃ
    0.07
    istically
    0.07
    Act Density 0.034%

    No Known Activations