INDEX
    Explanations

    the word "men."

    repeated references to "men" throughout the text

    New Auto-Interp
    Negative Logits
    Deal
    -0.76
    REDACTED
    -0.75
    IVERS
    -0.74
    EV
    -0.73
     Pwr
    -0.71
    Accessory
    -0.69
    ITED
    -0.68
    Allows
    -0.68
    REC
    -0.67
    Berry
    -0.67
    POSITIVE LOGITS
    opausal
    1.21
    endez
    1.19
    volent
    1.19
    uscript
    1.11
    ager
    1.07
    orah
    1.02
    folk
    0.99
    aced
    0.99
    aces
    0.97
    gling
    0.90
    Act Density 0.048%

    No Known Activations