INDEX
    Explanations

    descriptions

    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.87
    StoryboardSegue
    -0.84
     pleaſure
    -0.84
     purpoſe
    -0.83
     Chriftian
    -0.81
     nahilalakip
    -0.80
     Jefus
    -0.80
     Shakspeare
    -0.80
     Monfieur
    -0.79
     pngtree
    -0.78
    POSITIVE LOGITS
     of
    0.67
     plan
    0.54
    s
    0.53
     regular
    0.52
     Plan
    0.51
     video
    0.50
     fint
    0.50
     Stand
    0.48
     tri
    0.47
    Plan
    0.47
    Act Density 1.806%

    No Known Activations