INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     diffus
    0.46
     scans
    0.43
     datasets
    0.42
     diagrams
    0.42
     scalar
    0.39
     diligent
    0.39
     daily
    0.39
     diagram
    0.38
     notifications
    0.38
     nanom
    0.38
    POSITIVE LOGITS
     fundraiser
    0.85
     picnic
    0.84
     Picnic
    0.83
     brunch
    0.82
     Brunch
    0.77
     extravaganza
    0.77
     Celebration
    0.75
     luncheon
    0.73
     barbecue
    0.71
     fundraising
    0.70
    Act Density 0.013%

    No Known Activations