INDEX
    Explanations

    terms related to authoritarianism and totalitarianism

    New Auto-Interp
    Negative Logits
    -bodied
    -0.07
    -area
    -0.07
    ogg
    -0.06
    enal
    -0.06
    oom
    -0.06
    posable
    -0.06
    ìĹ´
    -0.06
    aida
    -0.06
    scribe
    -0.06
    _KERNEL
    -0.06
    POSITIVE LOGITS
    ism
    0.09
     thumb
    0.08
     rule
    0.08
    isms
    0.07
    ships
    0.07
    -leaning
    0.07
    SHIP
    0.07
     regimes
    0.07
    like
    0.06
     ÑĢежим
    0.06
    Act Density 0.014%

    No Known Activations