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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .www
    -0.16
    Ñħи
    -0.15
    dera
    -0.15
    lej
    -0.14
     incel
    -0.14
    (æľ¨
    -0.13
    ">ÃĹ</
    -0.13
    ücken
    -0.13
    illes
    -0.13
    _READONLY
    -0.13
    POSITIVE LOGITS
     com
    0.22
     Petersburg
    0.19
     then
    0.15
    arti
    0.15
     but
    0.15
     But
    0.14
     edu
    0.14
    :
    0.14
     gov
    0.14
     These
    0.14
    Act Density 0.313%

    No Known Activations