INDEX
    Explanations

    actions related to sharing, engaging, and interacting on social media platforms

    calls to action or requests for user engagement

    New Auto-Interp
    Negative Logits
    pher
    -0.77
     FIG
    -0.63
     dece
    -0.61
     absent
    -0.59
    riers
    -0.59
     cad
    -0.59
    shown
    -0.57
     prol
    -0.56
     distortion
    -0.56
    ileaks
    -0.56
    POSITIVE LOGITS
    Subscribe
    0.89
     Cancel
    0.86
     Subscribe
    0.79
    iframe
    0.75
     Email
    0.72
    ãĥĥãĥī
    0.66
     guiActive
    0.65
    Privacy
    0.65
     subscribing
    0.64
    ocity
    0.64
    Act Density 0.105%

    No Known Activations