INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    IO
    -0.09
     IO
    -0.08
    _io
    -0.08
    _HINT
    -0.08
    _IO
    -0.08
     Freel
    -0.07
    ODES
    -0.07
    ыз
    -0.07
    _hint
    -0.07
     Holm
    -0.07
    POSITIVE LOGITS
    -era
    0.12
     ideology
    0.11
     malign
    0.09
     vile
    0.09
     factions
    0.09
     militar
    0.09
    0.09
     conspiracy
    0.09
     faction
    0.09
     ideological
    0.09
    Act Density 0.011%

    No Known Activations