INDEX
    Explanations

    internet slang

    New Auto-Interp
    Negative Logits
     Carnegie
    -0.09
     شاع
    -0.08
     Thomson
    -0.08
    pele
    -0.08
     existem
    -0.08
     sparkle
    -0.08
     Hann
    -0.08
     placas
    -0.08
    andag
    -0.08
     Palmas
    -0.08
    POSITIVE LOGITS
     fucked
    0.08
     follower
    0.08
     kud
    0.08
     Appreciation
    0.08
    ürk
    0.07
     froze
    0.07
     apologized
    0.07
     facil
    0.07
    0.07
    ,请
    0.07
    Act Density 0.013%

    No Known Activations