INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     enjoy
    -1.16
     enjoying
    -1.05
     enjoys
    -0.99
     Enjoy
    -0.93
    Enjoy
    -0.92
    ftagPool
    -0.90
     disfrutando
    -0.86
    enjoy
    -0.84
    Enjoying
    -0.80
     disfru
    -0.79
    POSITIVE LOGITS
     AppModule
    0.64
     contextLoads
    0.60
    osoba
    0.58
    0.58
     Majefty
    0.57
    AsUp
    0.56
    obacterium
    0.56
    ]--;
    0.55
     Carnegie
    0.54
    Vezi
    0.54
    Act Density 0.257%

    No Known Activations