INDEX
    Explanations

    names and titles of people in a political context

    New Auto-Interp
    Negative Logits
    iseaux
    -0.55
    OPSIS
    -0.47
     '!
    -0.46
    AAB
    -0.46
    >>;
    -0.45
    ्म
    -0.45
     Acero
    -0.45
     poffible
    -0.44
     ziua
    -0.44
     viata
    -0.44
    POSITIVE LOGITS
    twimg
    0.84
    migrationBuilder
    0.72
    UnsafeEnabled
    0.64
    nytimes
    0.64
    UnusedPrivate
    0.63
    rungsseite
    0.62
    InputTagHelper
    0.62
     Wicidata
    0.62
     المعيارى
    0.61
    awtextra
    0.61
    Act Density 0.073%

    No Known Activations