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

    Neuronpedia

    INDEX
    Explanations

    formatted string patterns and numerical representations, particularly those related to percentages and scientific notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.69
    ruptedException
    -0.58
    -
    -0.55
     in
    -0.52
    .
    -0.48
     (
    -0.48
    /*
    -0.47
     os
    -0.47
     //
    -0.47
     of
    -0.46
    POSITIVE LOGITS
     $_"
    0.95
    UrlResolution
    0.94
     auffi
    0.91
     ſeveral
    0.90
     iſt
    0.90
     reaſon
    0.89
    enumii
    0.89
     Monfieur
    0.89
     diſt
    0.88
     myſelf
    0.87
    Act Density 0.091%

    No Known Activations