INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     terrenos
    -0.08
    ulados
    -0.07
     sons
    -0.07
     (-
    -0.07
     locom
    -0.07
     inmediata
    -0.07
     ontmo
    -0.07
    ~-
    -0.07
     saturation
    -0.07
     satur
    -0.07
    POSITIVE LOGITS
     krist
    0.12
    0.11
     glass
    0.11
    Glass
    0.11
    0.11
    透明
    0.11
     translucent
    0.11
     vidrio
    0.11
     kaca
    0.10
     transparency
    0.10
    Act Density 0.071%

    No Known Activations