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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sup
    -0.53
     las
    -0.47
    uş
    -0.47
    las
    -0.45
     Bri
    -0.45
     C
    -0.44
    ,
    -0.42
     F
    -0.42
    p
    -0.42
     G
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.91
    ."</
    0.89
    extAlignment
    0.88
     NSCoder
    0.87
    Демографія
    0.87
     ویکی‌پدیای
    0.87
    pyplot
    0.85
     }}"></
    0.83
     lenker
    0.83
     Bourgoin
    0.82
    Act Density 0.099%

    No Known Activations