INDEX
    Explanations

    references to the Super Bowl

    references to the Super Bowl and related events

    New Auto-Interp
    Negative Logits
     Seym
    -0.77
    gow
    -0.76
     guiActiveUn
    -0.73
    ...]
    -0.73
    assetsadobe
    -0.69
    theless
    -0.69
    76561
    -0.68
     whispers
    -0.65
    OPLE
    -0.63
    Downloadha
    -0.62
    POSITIVE LOGITS
    visors
    1.28
    visor
    1.25
    nova
    1.10
    imposed
    1.09
    marine
    1.05
    visory
    1.00
    vised
    0.95
    natural
    0.94
    intend
    0.93
    cedes
    0.92
    Act Density 0.014%

    No Known Activations