INDEX
    Explanations

    mentions related to the Super Bowl

    references to the Super Bowl and related events

    New Auto-Interp
    Negative Logits
    gow
    -0.88
    ...]
    -0.81
    aughs
    -0.73
    76561
    -0.72
     whispers
    -0.70
    REDACTED
    -0.69
    edin
    -0.68
     Nicholson
    -0.67
    theless
    -0.66
     Seym
    -0.65
    POSITIVE LOGITS
    visor
    1.12
    visors
    1.05
    nova
    1.05
    imposed
    0.98
    marine
    0.94
    visory
    0.92
    natural
    0.91
    oshenko
    0.88
    itialized
    0.87
    sequent
    0.81
    Act Density 0.010%

    No Known Activations