INDEX
    Explanations

    references to surveillance technology and its implications

    New Auto-Interp
    Negative Logits
    ofire
    -0.14
    _DEPRECATED
    -0.14
     vandal
    -0.14
    conc
    -0.14
    _bot
    -0.14
     peso
    -0.13
    enin
    -0.13
    itus
    -0.13
    gnore
    -0.13
     Conc
    -0.13
    POSITIVE LOGITS
     surveillance
    0.44
     Surveillance
    0.38
     surve
    0.35
     spy
    0.30
     facial
    0.30
     spying
    0.28
     Facial
    0.28
     privacy
    0.28
     sno
    0.28
    -sur
    0.27
    Act Density 0.109%

    No Known Activations