INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Polsek
    -0.56
    oursquare
    -0.56
    atzes
    -0.55
     dõi
    -0.54
    bär
    -0.54
     Chinois
    -0.53
    educt
    -0.52
    EntityType
    -0.52
    pshot
    -0.51
    cheid
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.64
     فريبيس
    0.62
     صوتيه
    0.59
     FontWeight
    0.50
    tagext
    0.50
    tttt
    0.49
    InputBorder
    0.49
    MessageTagHelper
    0.49
    sendStatus
    0.48
    slidesToShow
    0.48
    Act Density 0.010%

    No Known Activations