INDEX
    Explanations

    references to sports teams and their upcoming games or performances

    New Auto-Interp
    Negative Logits
    RetentionPolicy
    -0.52
    CreateModel
    -0.48
    Референце
    -0.48
    javac
    -0.47
    Hentet
    -0.46
     disambiguazione
    -0.46
    acyjnych
    -0.46
     yaşad
    -0.45
    PYX
    -0.45
     따
    -0.44
    POSITIVE LOGITS
     enter
    0.81
     face
    0.79
     enters
    0.72
     host
    0.66
     travel
    0.65
     faces
    0.64
     travels
    0.61
    enter
    0.61
    fromnode
    0.60
     welcome
    0.60
    Act Density 0.202%

    No Known Activations