INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     undertakings
    0.44
     vaccinations
    0.44
     حول
    0.43
     presencia
    0.43
    0.42
     sorrows
    0.41
     tassa
    0.41
     migrations
    0.41
    ității
    0.41
     demonstrations
    0.41
    POSITIVE LOGITS
    red
    0.48
     was
    0.44
    jud
    0.41
     place
    0.41
     seemed
    0.41
    Red
    0.40
    ifes
    0.39
     était
    0.39
    re
    0.39
    judge
    0.38
    Act Density 0.000%

    No Known Activations