INDEX
    Explanations

    references to legal issues and news articles

    New Auto-Interp
    Negative Logits
    .instagram
    -0.19
    atak
    -0.18
    Instagram
    -0.17
     Medium
    -0.16
    =https
    -0.15
    emoji
    -0.15
     GDPR
    -0.15
     Patreon
    -0.15
     @_
    -0.15
    }}],↵
    -0.15
    POSITIVE LOGITS
     Spinner
    0.22
    UPI
    0.21
    .guard
    0.20
     iht
    0.20
    Associated
    0.19
     salon
    0.19
     lat
    0.19
    kits
    0.18
     Associated
    0.18
     Salon
    0.18
    Act Density 0.167%

    No Known Activations