INDEX
    Explanations

    words related to extremism and terrorism

    fragments that imply legal terms or judicial processes

    New Auto-Interp
    Negative Logits
    200000
    -0.73
     Remastered
    -0.67
    TPPStreamerBot
    -0.64
    DAQ
    -0.62
    Mob
    -0.61
    ItemTracker
    -0.60
    tackle
    -0.60
    natureconservancy
    -0.60
    gdala
    -0.58
     BCC
    -0.57
    POSITIVE LOGITS
    levard
    0.78
    ucha
    0.71
    etime
    0.66
    ère
    0.65
     Ferry
    0.65
     Jenner
    0.63
    ansk
    0.63
    Initialized
    0.63
    uda
    0.63
    aire
    0.63
    Act Density 0.283%

    No Known Activations