INDEX
    Explanations

    references to official statements, documents, and policies

    New Auto-Interp
    Negative Logits
     officially
    -0.18
    Official
    -0.16
    official
    -0.16
    à¸Ńà¸Ķ
    -0.16
     official
    -0.16
     Officials
    -0.16
     Official
    -0.16
    å®ĺç½ij
    -0.16
    orian
    -0.15
    affected
    -0.15
    POSITIVE LOGITS
    dom
    0.37
    dehyde
    0.28
    ity
    0.23
    /legal
    0.23
    -san
    0.22
    ized
    0.22
    -dom
    0.21
    mente
    0.21
     sanction
    0.20
    ised
    0.19
    Act Density 0.031%

    No Known Activations