INDEX
    Explanations

    phrases related to prison sentences and incarceration

    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.06
    4:0.08
    5:0.03
    6:0.05
    7:0.29
    8:0.04
    9:0.04
    10:0.13
    11:0.12
    Negative Logits
    yip
    -1.81
    DragonMagazine
    -1.61
     contrace
    -1.46
    NetMessage
    -1.46
    iferation
    -1.42
     weap
    -1.40
    TPPStreamerBot
    -1.40
     listener
    -1.39
    -1.39
     cue
    -1.36
    POSITIVE LOGITS
     Pont
    1.35
     blocks
    1.33
    pps
    1.24
     solitary
    1.24
    estern
    1.24
     Schro
    1.23
    estyles
    1.19
    orean
    1.19
     Livingston
    1.18
    oppy
    1.17
    Act Density 0.002%

    No Known Activations