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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and quotation marks used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.62
    AutoScaleMode
    -0.59
    Pyx
    -0.49
    tagHelperRunner
    -0.49
    cvtColor
    -0.47
     informée
    -0.47
     ***!
    -0.43
     Fels
    -0.42
     Matching
    -0.42
    endregion
    -0.41
    POSITIVE LOGITS
     étoit
    0.61
     enfans
    0.59
     tenisky
    0.54
    KommentareTeilen
    0.53
     esternos
    0.52
     desmotivaciones
    0.52
     auroit
    0.50
    MENAFN
    0.50
     scienza
    0.48
     indígen
    0.48
    Act Density 0.241%

    No Known Activations