INDEX
    Explanations

    Quoted speech attribution

    New Auto-Interp
    Negative Logits
    Exc
    -0.06
     Benny
    -0.06
    kish
    -0.06
     Injectable
    -0.06
     Wind
    -0.06
     NFL
    -0.05
    ("//
    -0.05
     sağ
    -0.05
    @api
    -0.05
     conservatives
    -0.05
    POSITIVE LOGITS
     kata
    0.07
     naken
    0.07
     Saints
    0.06
    iquer
    0.06
    usz
    0.06
    hoa
    0.06
    ляється
    0.06
    Allocate
    0.06
     latino
    0.06
     сб
    0.06
    Act Density 0.046%

    No Known Activations