INDEX
    Explanations

    expressions of admiration

    New Auto-Interp
    Negative Logits
    有一定的
    0.57
    较为
    0.46
    有力
    0.45
     sizable
    0.45
    奇怪
    0.44
     sizeable
    0.43
     dość
    0.43
    0.43
     unattractive
    0.42
     raczej
    0.42
    POSITIVE LOGITS
     AMAZING
    2.55
     amazing
    2.36
     fantastic
    2.27
    amazing
    2.23
     incredible
    2.17
     fabulous
    2.17
     fantast
    2.16
     wonderful
    2.09
     marvelous
    2.09
    fantastic
    2.09
    Act Density 1.263%

    No Known Activations