INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Número
    -0.10
     الحوار
    -0.09
     números
    -0.09
     Telephone
    -0.09
    .number
    -0.08
     tasted
    -0.08
     Numbers
    -0.08
    sev
    -0.08
     numéro
    -0.08
     وعد
    -0.08
    POSITIVE LOGITS
     UAV
    0.16
     drone
    0.16
     drones
    0.15
     Drone
    0.15
     aerial
    0.15
     swarm
    0.14
    Drone
    0.14
     DJI
    0.13
     helicopters
    0.12
     footage
    0.11
    Act Density 0.027%

    No Known Activations