INDEX
    Explanations

    references to government control and totalitarianism

    New Auto-Interp
    Negative Logits
    piel
    -0.15
    094
    -0.15
    _AA
    -0.15
    alias
    -0.15
    537
    -0.14
    urtles
    -0.14
    QS
    -0.14
     Sullivan
    -0.14
    IPS
    -0.14
    .toCharArray
    -0.14
    POSITIVE LOGITS
    AtA
    0.15
    ARING
    0.14
    dub
    0.14
    stub
    0.14
    Ħ
    0.14
    ace
    0.14
     cruc
    0.14
     çϾ
    0.14
    .CV
    0.14
    bjerg
    0.13
    Act Density 0.422%

    No Known Activations