INDEX
    Explanations

    the phrase "Game of Thrones."

    the phrase "Game of" followed by various contextually relevant terms

    New Auto-Interp
    Negative Logits
    igham
    -0.87
    awei
    -0.71
     trustworthy
    -0.63
    anty
    -0.63
    ategory
    -0.62
    anchester
    -0.62
    ctr
    -0.62
    jriwal
    -0.60
     veil
    -0.60
     vest
    -0.60
    POSITIVE LOGITS
     Thrones
    0.96
    TAG
    0.88
     TAG
    0.72
    owitz
    0.72
    \-
    0.67
     Powered
    0.66
     luck
    0.66
     Friendship
    0.65
     Roses
    0.65
     damned
    0.64
    Act Density 0.088%

    No Known Activations