INDEX
    Explanations

    phrases referencing political or social rights issues

    New Auto-Interp
    Negative Logits
    anos
    -0.17
    iral
    -0.15
    cke
    -0.15
    oyal
    -0.15
    oruÄį
    -0.14
     narc
    -0.14
     factorial
    -0.14
     addCriterion
    -0.14
    arra
    -0.14
    ÑĨов
    -0.14
    POSITIVE LOGITS
    rve
    0.16
    mb
    0.16
    MB
    0.15
    osten
    0.15
    ivate
    0.14
    ymb
    0.14
    .Wrap
    0.13
    afia
    0.13
    erved
    0.13
    idges
    0.13
    Act Density 0.260%

    No Known Activations