INDEX
    Explanations

    the mention of specific names, especially related to sports and entertainment

    names of people, particularly in contexts involving competition or notable events

    New Auto-Interp
    Negative Logits
    cap
    -0.88
    gered
    -0.84
    enium
    -0.81
    iage
    -0.80
    yll
    -0.79
    ership
    -0.77
    oria
    -0.76
    seless
    -0.74
    rec
    -0.74
    yrim
    -0.73
    POSITIVE LOGITS
     Browne
    0.89
    agher
    0.80
     millenn
    0.79
     Barnett
    0.73
     livest
    0.72
    igham
    0.71
    staking
    0.70
    ignty
    0.68
     Pwr
    0.68
     challeng
    0.66
    Act Density 0.017%

    No Known Activations