INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     giúp
    -0.07
     planar
    -0.07
     @
    -0.07
     લોકોને
    -0.07
     playful
    -0.07
    ечки
    -0.07
     children's
    -0.06
     facility
    -0.06
    сят
    -0.06
     controversial
    -0.06
    POSITIVE LOGITS
     iniciou
    0.10
     underwent
    0.10
     अवस्था
    0.09
     undergo
    0.09
     stanje
    0.09
    投入
    0.08
     iniciado
    0.08
    发动
    0.08
    .fb
    0.08
     motor
    0.08
    Act Density 0.007%

    No Known Activations