INDEX
    Explanations

    concepts related to societal organization and control

    New Auto-Interp
    Negative Logits
    759
    -0.16
    umba
    -0.16
    aft
    -0.15
    amarin
    -0.15
    ros
    -0.15
    awner
    -0.15
    orget
    -0.15
    ERO
    -0.15
    resco
    -0.14
    ervers
    -0.14
    POSITIVE LOGITS
     Tactics
    0.25
     tactics
    0.24
     methods
    0.22
     Methods
    0.21
     Means
    0.20
     sacrifices
    0.19
     sacrifice
    0.19
     sometimes
    0.19
    Means
    0.19
    Methods
    0.18
    Act Density 0.208%

    No Known Activations