INDEX
    Explanations

    references to political candidates and nominations

    New Auto-Interp
    Negative Logits
    keit
    -0.17
    .gstatic
    -0.15
    oya
    -0.15
    ctors
    -0.15
    shire
    -0.14
    å¹ķ
    -0.14
    ides
    -0.14
    med
    -0.14
    mary
    -0.14
    thing
    -0.14
    POSITIVE LOGITS
    780
    0.15
    -regexp
    0.15
    ioned
    0.15
    ADC
    0.14
    iments
    0.14
    ooled
    0.14
     Steele
    0.14
     terre
    0.14
    ets
    0.14
    ughter
    0.14
    Act Density 0.046%

    No Known Activations