INDEX
    Explanations

    references to discrimination based on sexual orientation

    New Auto-Interp
    Negative Logits
    uckland
    -0.74
     Purg
    -0.68
    jam
    -0.67
    answered
    -0.65
    jet
    -0.65
    nan
    -0.64
    Edit
    -0.64
     upd
    -0.63
     Loop
    -0.63
    cean
    -0.62
    POSITIVE LOGITS
     nationality
    1.12
     ethnicity
    1.07
     gender
    0.96
     resemblance
    0.87
     colour
    0.87
     creed
    0.85
     whim
    0.85
     whims
    0.85
     likeness
    0.85
     merit
    0.83
    Act Density 0.239%

    No Known Activations