INDEX
    Explanations

    references to authors and their literary works

    New Auto-Interp
    Negative Logits
    iastes
    -0.67
    Geplaatst
    -0.65
    AsUp
    -0.62
    altham
    -0.56
    UIControlState
    -0.56
    ultat
    -0.50
    ticles
    -0.49
    บ้าง
    -0.48
    ulite
    -0.48
    lewati
    -0.47
    POSITIVE LOGITS
     Cosplay
    0.77
     cosplay
    0.76
    cosplay
    0.70
    Xna
    0.69
    deviantart
    0.67
    Heya
    0.66
     comics
    0.66
     waifu
    0.65
     Fandom
    0.64
    Personensuche
    0.64
    Act Density 0.485%

    No Known Activations