INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Gambling
    -0.09
     Gulf
    -0.08
     paro
    -0.08
     അന്ത
    -0.07
     terro
    -0.07
     오는
    -0.07
     trạng
    -0.07
     gambling
    -0.07
    ,parent
    -0.07
     pregnancies
    -0.07
    POSITIVE LOGITS
     screwdriver
    0.10
    abrik
    0.09
     cabinet
    0.09
     kecil
    0.09
     rumm
    0.08
    kari
    0.08
    -icons
    0.08
    lery
    0.08
    heber
    0.08
     butterknife
    0.08
    Act Density 0.004%

    No Known Activations