INDEX
    Explanations

    references to churches or church-related activities

    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.69
     Rog
    -0.67
    LER
    -0.67
     neurot
    -0.65
    nir
    -0.63
     Haf
    -0.62
    othy
    -0.62
    berman
    -0.62
    Consumer
    -0.61
    schild
    -0.61
    POSITIVE LOGITS
    goers
    1.28
    yard
    1.11
     fathers
    0.92
    esan
    0.90
    going
    0.90
    yards
    0.89
     bells
    0.88
     choir
    0.88
    church
    0.84
     congregation
    0.84
    Act Density 0.024%

    No Known Activations