INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Pago
    -0.10
    верс
    -0.09
     nightmare
    -0.09
     pago
    -0.08
    -0.08
    _pago
    -0.08
    是真
    -0.08
     nightmares
    -0.08
    	Version
    -0.08
    huis
    -0.08
    POSITIVE LOGITS
     distracting
    0.10
     handy
    0.10
     idle
    0.10
     nhẹ
    0.10
    Idle
    0.10
    .misc
    0.09
     reposition
    0.09
     discreet
    0.09
     débit
    0.08
     cigarette
    0.08
    Act Density 0.070%

    No Known Activations