INDEX
    Explanations

    references to sports teams, particularly the Cleveland Browns

    New Auto-Interp
    Negative Logits
    multipl
    -0.74
    ging
    -0.72
    ledged
    -0.70
    ical
    -0.70
    icide
    -0.69
     quo
    -0.69
    sent
    -0.67
    undo
    -0.67
    uador
    -0.67
    iasis
    -0.66
    POSITIVE LOGITS
     Cavaliers
    1.13
     Clinic
    1.10
     Heights
    1.07
     Browns
    0.95
     Indians
    0.93
     Orchestra
    0.78
    ville
    0.78
     Plain
    0.77
     skyline
    0.76
     Hopkins
    0.72
    Act Density 0.024%

    No Known Activations