INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kin
    -0.08
    DDR
    -0.08
    _proto
    -0.08
    Biography
    -0.08
     građ
    -0.07
     katt
    -0.07
     иг
    -0.07
     actor
    -0.07
     kole
    -0.07
     quién
    -0.07
    POSITIVE LOGITS
     hydrocar
    0.10
    0.09
     combustível
    0.09
     combustion
    0.09
     топлива
    0.09
     gases
    0.08
    0.08
     ocorre
    0.08
     pellets
    0.08
    事故
    0.08
    Act Density 0.004%

    No Known Activations