INDEX
    Explanations

    references to law enforcement actions and public protests

    New Auto-Interp
    Negative Logits
    alloca
    -0.16
    allis
    -0.15
    úi
    -0.15
    znam
    -0.15
    estre
    -0.14
    uzey
    -0.14
    alem
    -0.14
     defaultManager
    -0.14
    affles
    -0.14
    monton
    -0.14
    POSITIVE LOGITS
    oad
    0.17
    64
    0.16
    st
    0.14
    еÑĢг
    0.14
    ach
    0.14
    olf
    0.14
    63
    0.14
    ops
    0.14
     Naz
    0.14
    imer
    0.14
    Act Density 0.493%

    No Known Activations