INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ARGE
    -0.07
     pine
    -0.06
    aces
    -0.06
    Pane
    -0.06
     blanks
    -0.06
    GIN
    -0.06
     Uk
    -0.06
     Goa
    -0.06
    BC
    -0.06
     Bits
    -0.06
    POSITIVE LOGITS
    政治
    0.07
     Steering
    0.06
    棋牌
    0.06
     doctr
    0.06
     kvinna
    0.06
    undry
    0.06
    Floating
    0.06
    ingroup
    0.06
     Palestin
    0.06
     dolay
    0.06
    Act Density 0.010%

    No Known Activations