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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.47
    ↵↵
    -0.27
    ↵ ↵
    -0.24
    ↵			↵
    -0.22
    &nbsp
    -0.21
    ↵		↵
    -0.21
    ,
    -0.20
    ↵	↵
    -0.20
    ↵  ↵
    -0.19
    ↵				↵
    -0.18
    POSITIVE LOGITS
    nodoc
    0.29
    -↵↵
    0.23
    -(
    0.22
     :
    0.21
    _
    0.20
    <
    0.20
    s
    0.19
    [
    0.19
    nth
    0.19
    rolley
    0.19
    Act Density 0.037%

    No Known Activations