INDEX
    Explanations

    mentions of controversial or political topics and figures

    references to cultural or political issues involving social justice and discrimination

    New Auto-Interp
    Negative Logits
     UNCLASSIFIED
    -0.73
     anecd
    -0.72
     pse
    -0.68
    theless
    -0.65
     millenn
    -0.60
    lvl
    -0.59
    ouver
    -0.58
     :=
    -0.56
     rhet
    -0.55
    retty
    -0.55
    POSITIVE LOGITS
     Donald
    0.73
     Adolf
    0.71
     transgender
    0.67
    âĢİ
    0.65
    Brexit
    0.64
    ihadi
    0.63
     Belfast
    0.62
     ObamaCare
    0.60
    Islam
    0.60
     Ebola
    0.60
    Act Density 1.958%

    No Known Activations