INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     sweeping
    -0.08
     banning
    -0.07
     year's
    -0.07
    awning
    -0.07
    حين
    -0.07
     eternal
    -0.07
    -0.07
    ศัพท์
    -0.07
     Eternal
    -0.07
    yaan
    -0.07
    POSITIVE LOGITS
     assurance
    0.08
     derm
    0.08
     Pix
    0.08
     portability
    0.07
    Liquid
    0.07
     이하
    0.07
     Oils
    0.07
    manship
    0.07
    gar
    0.07
     Springs
    0.07
    Act Density 0.005%

    No Known Activations