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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and variations in their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.23
    ah
    -0.16
    ummer
    -0.15
     же
    -0.15
    -ÑĤаки
    -0.14
    iry
    -0.14
    allee
    -0.14
    usty
    -0.13
    xiety
    -0.13
    uzzle
    -0.13
    POSITIVE LOGITS
    s
    0.17
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.17
     latter
    0.16
    phans
    0.16
    ,,,
    0.16
    loor
    0.15
    ,,,,,,,,
    0.15
    cgi
    0.15
    ylland
    0.14
    ska
    0.14
    Act Density 0.105%

    No Known Activations