INDEX
    Explanations

    content related to family and social gatherings

    New Auto-Interp
    Negative Logits
     Wedding
    -0.15
    rosso
    -0.14
     pl
    -0.14
     Holidays
    -0.14
     snack
    -0.14
    -END
    -0.14
    ابر
    -0.14
     weddings
    -0.14
    omin
    -0.13
    leep
    -0.13
    POSITIVE LOGITS
     downtown
    0.18
    IODevice
    0.16
     shopping
    0.16
    .trip
    0.15
     nearby
    0.15
     kino
    0.15
    ToLocal
    0.15
    çĦ¼
    0.15
     cinema
    0.14
     movie
    0.14
    Act Density 0.223%

    No Known Activations