INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ]--;
    -0.56
     accompagne
    -0.54
     виправивши
    -0.52
     rappresenta
    -0.51
     hâte
    -0.50
     nôtre
    -0.50
    Matches
    -0.49
     colgantes
    -0.48
     lampe
    -0.47
     prêtres
    -0.46
    POSITIVE LOGITS
     week
    0.67
     year
    0.64
    ///</
    0.64
    Pyx
    0.63
    istoitu
    0.63
     past
    0.62
    astify
    0.60
    +#+
    0.60
     month
    0.58
    windowFixed
    0.58
    Act Density 0.036%

    No Known Activations