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

    Neuronpedia

    INDEX
    Explanations

    occurrences of commas separating items or clauses in a text

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

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.41
    Välislingid
    -0.34
    dafx
    -0.30
     tı
    -0.30
    をつける
    -0.28
    Excelente
    -0.28
     avantages
    -0.28
     attentes
    -0.28
     yapt
    -0.27
     íntimo
    -0.27
    POSITIVE LOGITS
    ſammen
    0.60
    enumii
    0.59
     dieſes
    0.59
     Dieſe
    0.59
     $_(
    0.59
     ſeinen
    0.59
     $_=
    0.58
    ſicht
    0.58
    [@BOS@]
    0.58
    <unused3>
    0.58
    Act Density 0.021%

    No Known Activations