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

    Neuronpedia

    INDEX
    Explanations

    blocks of text formatted as documentation or comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.58
    FTFY
    -0.58
     ſind
    -0.56
    parsedMessage
    -0.55
     Majefty
    -0.54
     Algorithm
    -0.54
    htbp
    -0.53
    Демографія
    -0.53
     improvis
    -0.52
     verſ
    -0.52
    POSITIVE LOGITS
     *
    1.62
     **
    0.88
     $*
    0.71
     *
    0.70
     $*$
    0.66
     ***
    0.65
     *_
    0.65
     *(
    0.63
     *__
    0.62
     *>
    0.62
    Act Density 0.221%

    No Known Activations