INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.68
     Supplemental
    -0.65
     humiliating
    -0.65
     narratives
    -0.65
     tense
    -0.64
     budgetary
    -0.64
     polled
    -0.64
     fitting
    -0.64
     rounded
    -0.63
     relocation
    -0.63
    POSITIVE LOGITS
    gmail
    2.16
    yahoo
    1.80
    hot
    1.39
    microsoft
    1.38
    earth
    1.37
    hillary
    1.36
    debian
    1.35
    bleacher
    1.33
    mail
    1.26
    lists
    1.25
    Act Density 0.012%

    No Known Activations