INDEX
    Explanations

    punctuation and specific structural elements in the text

    Punctuation followed by a capitalized word

    narrative sequences and observations

    New Auto-Interp
    Negative Logits
    }")
    
    -0.69
    "):
    
    -0.67
    tôi
    -0.61
     nahilalakip
    -0.61
    '):
    
    -0.58
    ")));
    
    -0.58
    )";
    
    -0.58
    esserung
    -0.56
    存于互联网档案馆
    -0.55
     Waray
    -0.55
    POSITIVE LOGITS
    Seeing
    0.89
     seeing
    0.84
     Seeing
    0.84
     hearing
    0.77
     Hearing
    0.72
     although
    0.70
    seeing
    0.70
    Hearing
    0.69
     Faced
    0.66
     when
    0.66
    Act Density 0.021%

    No Known Activations