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

    Neuronpedia

    INDEX
    Explanations

    punctuation and quotation marks within text

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

    quoted speech ends with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solid
    -0.31
     dili
    -0.29
    +#+#
    -0.29
       
    -0.29
    पया
    -0.28
    出版年
    -0.28
    ্দ
    -0.28
     whole
    -0.27
     الحي
    -0.26
    AccessorTable
    -0.26
    POSITIVE LOGITS
     Италијани
    0.80
     betweenstory
    0.78
    WriteTagHelper
    0.68
    astéroïdes
    0.67
     مشين
    0.67
    tagext
    0.60
    ніципалі
    0.60
     VIDEOT
    0.59
    Rhestr
    0.57
     Italijani
    0.57
    Act Density 0.144%

    No Known Activations