INDEX
    Explanations

    themes of surveillance and authority in societal contexts

    New Auto-Interp
    Negative Logits
    ivec
    -0.17
    abbr
    -0.14
    axy
    -0.14
    etro
    -0.14
    elez
    -0.14
    asan
    -0.14
    zell
    -0.14
    odÃŃ
    -0.13
    astle
    -0.13
    uml
    -0.13
    POSITIVE LOGITS
     neust
    0.15
    íĺģ
    0.14
     extern
    0.14
     (:
    0.14
     pornos
    0.14
    ella
    0.13
    ãĥ¼ãĥª
    0.13
    ;amp
    0.13
     _____
    0.13
    еÑī
    0.13
    Act Density 0.029%

    No Known Activations