INDEX
    Explanations

    questions and statements related to social issues and awareness

    New Auto-Interp
    Negative Logits
    chwitz
    -0.16
    vÄĽt
    -0.16
    /Instruction
    -0.15
    ãİ
    -0.15
    å¬
    -0.15
    (æĹ¥
    -0.14
    senal
    -0.14
    addtogroup
    -0.14
     Prostitutas
    -0.14
    ().'/
    -0.13
    POSITIVE LOGITS
     your
    0.26
     America
    0.23
     '
    0.21
     our
    0.20
     the
    0.19
     today
    0.19
     these
    0.18
    0.17
     next
    0.16
     this
    0.16
    Act Density 0.275%

    No Known Activations