INDEX
    Explanations

    mentions of legal professionals, especially prosecutors

    New Auto-Interp
    Negative Logits
    lihood
    -0.81
    tz
    -0.70
    birth
    -0.68
    opic
    -0.68
    pid
    -0.67
    eem
    -0.66
    chron
    -0.65
     Sleeping
    -0.65
     Silent
    -0.63
    pt
    -0.62
    POSITIVE LOGITS
     prosecutors
    1.09
     prosecutor
    1.02
    avorite
    0.96
     Prosecutors
    0.95
    Prosecutors
    0.94
    heet
    0.91
     confir
    0.91
     GOODMAN
    0.88
     indicted
    0.86
     prosecut
    0.85
    Act Density 0.008%

    No Known Activations