INDEX
    Explanations

    occurrences of the pronoun "I"

    i and I variants, especially at start of phrase

    New Auto-Interp
    Negative Logits
     enfans
    -0.71
     uſed
    -0.68
     ſta
    -0.67
     raiſ
    -0.65
     themſelves
    -0.65
     unſ
    -0.62
    harusnya
    -0.61
     ſte
    -0.60
     juſ
    -0.60
     ſever
    -0.59
    POSITIVE LOGITS
     i
    0.91
     in
    0.68
     I
    0.66
    I
    0.66
    i
    0.65
     In
    0.62
     в
    0.57
     في
    0.53
    ใน
    0.49
    0.47
    Act Density 0.000%

    No Known Activations