INDEX
    Explanations

    names ending in -ian or -ary

    New Auto-Interp
    Negative Logits
    வான்
    0.45
    StarGo
    0.41
    0.40
    علی
    0.39
     以上
    0.39
     சகோ
    0.39
    TakeVideo
    0.39
     atlet
    0.39
     прекрасно
    0.39
     vibrant
    0.38
    POSITIVE LOGITS
     Pattern
    0.39
     Flux
    0.37
    xtures
    0.37
    flux
    0.37
     Traction
    0.37
     Active
    0.37
    Flux
    0.36
     Governmental
    0.36
    Textures
    0.36
     Rs
    0.36
    Act Density 0.003%

    No Known Activations