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

    Neuronpedia

    INDEX
    Explanations

    capital letters and significant punctuation marks in text

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

    letters A through D

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.66
     tartalomajánló
    -0.65
    utilisons
    -0.59
    Демографія
    -0.54
     الحره
    -0.52
     للاسماء
    -0.51
     OFDb
    -0.50
    ícola
    -0.50
     ujednoznacz
    -0.49
    RELAND
    -0.49
    POSITIVE LOGITS
     enfans
    0.46
     figliu
    0.40
    WithIOException
    0.39
    Dro
    0.35
     chữ
    0.34
    esModule
    0.34
     letters
    0.34
    ğraf
    0.33
     getItemId
    0.33
     letter
    0.33
    Act Density 0.084%

    No Known Activations