INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    rve
    -0.17
    andy
    -0.15
     nạn
    -0.15
    ovaly
    -0.15
    empo
    -0.14
    FileSystem
    -0.14
     Vog
    -0.14
     Mus
    -0.14
    ÙħÙĪØ¯
    -0.13
    itude
    -0.13
    POSITIVE LOGITS
    UTF
    0.25
    utf
    0.24
     utf
    0.21
    =UTF
    0.19
    iso
    0.19
     UTF
    0.19
    windows
    0.18
    ISO
    0.16
    =utf
    0.16
    umpt
    0.15
    Act Density 0.003%

    No Known Activations