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

    Neuronpedia

    INDEX
    Explanations

    quotation marks or apostrophes in text

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

    ‘ or ’ then a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exclude
    -0.46
    RDONLY
    -0.44
    GroupLayout
    -0.44
     exclude
    -0.41
     Rehab
    -0.41
    AutoModerator
    -0.39
     Lewandowski
    -0.39
    bern
    -0.38
    SQLiteDatabase
    -0.38
    kuuta
    -0.37
    POSITIVE LOGITS
     مشين
    0.63
     ’
    0.61
     ʻ
    0.56
     ‘
    0.55
     '
    0.54
     propOrder
    0.51
     resourceCulture
    0.50
     rodríguez
    0.49
    \{\\
    0.49
     fieldNum
    0.49
    Act Density 0.028%

    No Known Activations