INDEX
    Explanations

    foreign words and specific terms

    New Auto-Interp
    Negative Logits
     idol
    0.52
    [{{
    0.50
     auth
    0.49
     fans
    0.49
     admir
    0.48
     admirers
    0.48
     conspiring
    0.47
     admiration
    0.46
     admirer
    0.46
     eldest
    0.45
    POSITIVE LOGITS
     Kombination
    0.52
    يمكن
    0.50
     Schalt
    0.49
    گون
    0.49
    بد
    0.48
     Nancy
    0.47
     Nadia
    0.47
    OWA
    0.47
     الهدف
    0.46
     Amerikaanse
    0.46
    Act Density 0.000%

    No Known Activations