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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Motta
    -0.50
    SKA
    -0.45
    blis
    -0.45
     Moreira
    -0.45
     administrations
    -0.45
    YEARS
    -0.44
    ewear
    -0.43
     atve
    -0.43
    APAN
    -0.42
    UMBIA
    -0.42
    POSITIVE LOGITS
    util
    1.19
    io
    0.98
    awt
    0.94
    lang
    0.92
    nio
    0.91
    sql
    0.85
    math
    0.84
    time
    0.76
    net
    0.74
    text
    0.74
    Act Density 0.045%

    No Known Activations