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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    Punctuation separating sentences or clauses

    np_acts-logits-general · gemini-2.0-flash

    sentence initiators or list formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.92
     itſelf
    -0.91
     سكانية
    -0.86
    ientôt
    -0.81
     tartalomajánló
    -0.80
     pylint
    -0.80
     CHAPITRE
    -0.79
     שוליים
    -0.76
    enumi
    -0.74
    ihnach
    -0.74
    POSITIVE LOGITS
     The
    1.02
      
    0.79
     A
    0.75
     "
    0.74
     If
    0.72
     “
    0.72
     What
    0.71
     When
    0.68
     We
    0.67
     I
    0.67
    Act Density 0.223%

    No Known Activations