INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Hib
    -0.08
    .literal
    -0.08
     hib
    -0.08
     Adem
    -0.08
     Tsy
    -0.08
     Beat
    -0.07
    āti
    -0.07
     motivo
    -0.07
    >(()
    -0.07
     mismo
    -0.07
    POSITIVE LOGITS
     distancia
    0.09
     distances
    0.09
     distância
    0.09
    距离
    0.09
     distance
    0.09
    -distance
    0.09
     거리
    0.08
    distance
    0.08
    0.08
    afstand
    0.08
    Act Density 0.013%

    No Known Activations