INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Caf
    -0.08
     opat
    -0.07
     sophisticated
    -0.07
    unca
    -0.07
     sio
    -0.07
     Constantin
    -0.07
     Seng
    -0.07
     Sper
    -0.07
    -0.07
     silicon
    -0.07
    POSITIVE LOGITS
     pesos
    0.10
     aromas
    0.09
     kidneys
    0.09
     tempi
    0.08
     боли
    0.08
     assassin
    0.08
     Германии
    0.08
     عض
    0.08
    tm
    0.08
     sabores
    0.08
    Act Density 0.023%

    No Known Activations