INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    spheric
    -0.82
     McKay
    -0.74
     tangga
    -0.73
    onalds
    -0.69
    disciplinar
    -0.66
    前后
    -0.66
     Cricket
    -0.65
     Highland
    -0.65
     carp
    -0.65
     Jones
    -0.65
    POSITIVE LOGITS
     우리
    0.80
    Мекси
    0.79
    Dissertation
    0.77
    itesi
    0.73
    leid
    0.72
     introduit
    0.72
     完
    0.71
    を受けた
    0.70
     Contoh
    0.69
    ботинки
    0.69
    Act Density 0.036%

    No Known Activations