INDEX
    Explanations

    references to media and political commentary

    New Auto-Interp
    Negative Logits
     Snapchat
    -0.19
     snapchat
    -0.19
    WhatsApp
    -0.17
    Instagram
    -0.17
     Instagram
    -0.16
     Lyft
    -0.16
     WhatsApp
    -0.15
    óm
    -0.15
    202
    -0.14
    https
    -0.14
    POSITIVE LOGITS
     linkage
    0.26
     links
    0.25
    /link
    0.23
    -links
    0.23
    -linked
    0.23
    links
    0.23
     link
    0.22
     linked
    0.22
     linking
    0.22
    linky
    0.20
    Act Density 0.322%

    No Known Activations