INDEX
    Explanations

    mentions of the word "beach."

    New Auto-Interp
    Negative Logits
    Interstitial
    -0.77
    ocation
    -0.70
    alez
    -0.69
    Wilson
    -0.68
    iferation
    -0.65
    interstitial
    -0.64
    ilyn
    -0.64
    NESS
    -0.64
    ROR
    -0.62
    avery
    -0.62
    POSITIVE LOGITS
     beach
    1.13
     Beach
    1.00
     beaches
    0.94
     volleyball
    0.94
    side
    0.93
    front
    0.89
    pole
    0.85
    goers
    0.79
     bum
    0.79
     surfing
    0.79
    Act Density 0.007%

    No Known Activations