INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    anza
    -0.66
     Conclusion
    -0.65
    ģĸ
    -0.61
    ħĭ
    -0.60
    ĸļ
    -0.57
     stitches
    -0.57
    plot
    -0.56
    ¶ħ
    -0.55
    etc
    -0.54
     FIG
    -0.54
    POSITIVE LOGITS
    Follow
    0.90
    Subscribe
    0.88
     Follow
    0.82
     Email
    0.82
    twitter
    0.80
     UNCLASSIFIED
    0.78
    Email
    0.78
     subscribe
    0.73
     Subscribe
    0.70
    facebook
    0.70
    Act Density 1.140%

    No Known Activations