INDEX
    Explanations

    phrases indicating movement or direction

    New Auto-Interp
    Negative Logits
     SSC
    -0.69
    ürd
    -0.66
    Cree
    -0.62
     PSS
    -0.61
     Fung
    -0.60
    SSC
    -0.60
    ису
    -0.59
    herjee
    -0.58
     Abonnez
    -0.57
     Quảng
    -0.57
    POSITIVE LOGITS
     الحره
    0.88
    0.85
     ]
    
    0.79
    AndEndTag
    0.79
    Diweddarwch
    0.74
    unggulan
    0.74
    Personensuche
    0.73
    ItemBackground
    0.73
    migrationBuilder
    0.73
    cosm
    0.72
    Act Density 0.266%

    No Known Activations