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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.96
     الرياضيه
    -0.93
     onAnimation
    -0.86
     تضيفلها
    -0.69
     المعيارى
    -0.69
    CloseOperation
    -0.67
     שוליים
    -0.67
     للاسماء
    -0.66
    رشف
    -0.66
     мәкал
    -0.64
    POSITIVE LOGITS
    etine
    0.55
     simply
    0.54
    ята
    0.54
     habitudes
    0.54
     }],
    0.53
     Tenden
    0.53
     ever
    0.51
     fundamentales
    0.51
     mør
    0.51
    Tem
    0.49
    Act Density 0.076%

    No Known Activations