INDEX
    Explanations

    mentions of the word "Facebook" in various contexts

    references to Facebook and social media interactions

    New Auto-Interp
    Negative Logits
    iaz
    -0.72
    olar
    -0.69
     Virtue
    -0.67
    zin
    -0.67
    dinand
    -0.65
    liga
    -0.64
    RAG
    -0.64
    Downloadha
    -0.64
    ktop
    -0.64
    OPA
    -0.63
    POSITIVE LOGITS
     username
    0.96
     account
    0.91
     postings
    0.89
    username
    0.83
     avatar
    0.82
     commenter
    0.81
     outage
    0.81
     inbox
    0.80
     hashtag
    0.79
     emot
    0.78
    Act Density 0.065%

    No Known Activations