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

    Neuronpedia

    INDEX
    Explanations

    formatting and syntax elements in code or structured data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sqcup
    -0.78
    "}
    -0.75
     PGC
    -0.74
     huo
    -0.73
    ”]
    -0.71
    setVerticalGroup
    -0.71
    دانشنامهٔ
    -0.71
    oubtedly
    -0.70
     Kości
    -0.70
    "?>
    -0.70
    POSITIVE LOGITS
    :\
    0.93
     \
    0.88
     (\
    0.84
     {\
    0.82
    .\
    0.81
     "\
    0.79
    -\
    0.77
    %\
    0.77
    !\
    0.77
    =\
    0.76
    Act Density 0.499%

    No Known Activations