INDEX
    Explanations

    information related to news reporting and journalism

    instances of numerical data or statistics

    New Auto-Interp
    Negative Logits
    utic
    -0.69
     promptly
    -0.69
    uchs
    -0.68
     thereafter
    -0.66
     afterwards
    -0.65
     armour
    -0.65
     Gladiator
    -0.64
     endeav
    -0.64
    effect
    -0.64
     composing
    -0.63
    POSITIVE LOGITS
    rawdownloadcloneembedreportprint
    0.85
    Posted
    0.79
    PHOTOS
    0.78
     Caption
    0.77
     Related
    0.77
     VIDEOS
    0.75
    Scroll
    0.75
    posted
    0.73
    SEE
    0.71
    ³³³
    0.70
    Act Density 0.588%

    No Known Activations