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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.17
    nbsp
    -0.15
    ...]
    -0.15
    oldown
    -0.15
    $MESS
    -0.14
    ãĥªãĥ³ãĤ°
    -0.14
    =-=-=-=-=-=-=-=-
    -0.14
    %s
    -0.14
     ...(
    -0.14
    taboola
    -0.14
    POSITIVE LOGITS
    ‘
    0.19
    ...)↵
    0.17
    or
    0.16
    aka
    0.16
    ±
    0.16
    --)
    0.15
     http
    0.15
    ^^
    0.15
    __)
    0.15
    ,)
    0.14
    Act Density 0.437%

    No Known Activations