INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    dfa
    -0.08
    -0.08
     ceremonia
    -0.08
    .compile
    -0.08
     tabi
    -0.08
    .CL
    -0.08
     presenta
    -0.07
    -0.07
     działa
    -0.07
    사용
    -0.07
    POSITIVE LOGITS
     distance
    0.10
    距离
    0.09
     distances
    0.09
    0.09
    distance
    0.08
     расстоя
    0.08
    _distance
    0.08
     Bình
    0.08
     दूरी
    0.08
     Distance
    0.07
    Act Density 0.027%

    No Known Activations