INDEX
    Explanations

    names of athletes or sports figures

    New Auto-Interp
    Negative Logits
     poveznice
    -0.53
     abstrait
    -0.50
    Билгалдахарш
    -0.49
     BoxFit
    -0.47
    تفصیلات
    -0.45
    EndContext
    -0.44
     neutre
    -0.44
     resourceCulture
    -0.43
     TestBed
    -0.43
     ſhe
    -0.42
    POSITIVE LOGITS
    riezmann
    0.45
     الرياضيه
    0.43
     متعلقه
    0.41
     pagoda
    0.39
    aspectj
    0.39
    himovic
    0.39
     radium
    0.37
    0.37
    gebene
    0.36
    WriteBarrier
    0.36
    Act Density 0.276%

    No Known Activations