INDEX
    Explanations

    graphs and axes

    New Auto-Interp
    Negative Logits
     patents
    -0.07
    seed
    -0.06
    -0.06
    ायद
    -0.06
    _AMD
    -0.06
     TL
    -0.06
     chassis
    -0.06
    -0.06
     lust
    -0.06
    stakes
    -0.06
    POSITIVE LOGITS
    	bg
    0.07
    riel
    0.07
     distressed
    0.07
     friendly
    0.07
     programming
    0.06
     programme
    0.06
     guardians
    0.06
     Brendan
    0.06
     Ariel
    0.06
    year
    0.06
    Act Density 0.295%

    No Known Activations