INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    [channel
    -0.08
    (Link
    -0.08
     نش
    -0.08
     diário
    -0.08
    atm
    -0.07
    (channel
    -0.07
     poder
    -0.07
    -0.07
     amigo
    -0.07
     colega
    -0.07
    POSITIVE LOGITS
    	ST
    0.08
     STA
    0.08
     mott
    0.08
     Municipality
    0.08
     भर
    0.07
     rud
    0.07
     watercolor
    0.07
    _CAL
    0.07
     motto
    0.07
     Hermann
    0.07
    Act Density 0.014%

    No Known Activations