INDEX
    Explanations

    email addresses and related web links

    New Auto-Interp
    Negative Logits
     read
    -0.21
     reference
    -0.21
     title
    -0.21
     review
    -0.21
     text
    -0.20
     references
    -0.20
     comment
    -0.19
     content
    -0.19
     details
    -0.19
     news
    -0.19
    POSITIVE LOGITS
     Published
    0.33
     Email
    0.28
     Updated
    0.28
     Comments
    0.28
     Posted
    0.28
     Edited
    0.28
     Keywords
    0.27
     Comment
    0.27
     Copyright
    0.26
     Author
    0.26
    Act Density 0.322%

    No Known Activations