INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     diferença
    -0.08
    setq
    -0.08
    andak
    -0.08
    Difference
    -0.08
     Differences
    -0.08
     Difference
    -0.08
     escribió
    -0.08
     difference
    -0.08
     Nachrichten
    -0.08
    ुवार
    -0.08
    POSITIVE LOGITS
     aesthetics
    0.21
     aesthetic
    0.20
     aesthetically
    0.19
     эстет
    0.16
     estética
    0.15
     estet
    0.14
    漂亮
    0.14
     stylish
    0.13
     pleasing
    0.13
     sleek
    0.13
    Act Density 0.133%

    No Known Activations