INDEX
    Explanations

    themes related to violations of personal rights and the responses of individuals to these situations

    New Auto-Interp
    Negative Logits
    orton
    -0.15
    itaire
    -0.15
    adaki
    -0.14
    aç
    -0.14
     Cust
    -0.14
     èIJ¬
    -0.14
    quette
    -0.13
     SIGN
    -0.13
    oms
    -0.13
    931
    -0.13
    POSITIVE LOGITS
    ady
    0.17
    rå
    0.15
    usch
    0.15
    ewis
    0.15
    iddi
    0.15
    ushman
    0.14
    igen
    0.14
    arth
    0.14
    mino
    0.14
    amı
    0.14
    Act Density 0.873%

    No Known Activations