INDEX
    Explanations

    the presence of specific names of individuals

    New Auto-Interp
    Negative Logits
    didSet
    -0.61
     varandra
    -0.59
     propOrder
    -0.58
    mbggenerated
    -0.57
    uminense
    -0.57
     Tuchel
    -0.57
    sproble
    -0.56
     colonnes
    -0.54
    jmniej
    -0.53
     puertos
    -0.53
    POSITIVE LOGITS
     Seeder
    0.58
     Савезне
    0.55
    HideFlags
    0.55
    ocere
    0.49
     shot
    0.48
    0.48
    ParallelGroup
    0.47
     himself
    0.47
     Braut
    0.47
    RenderAtEndOf
    0.47
    Act Density 0.239%

    No Known Activations