INDEX
    Explanations

    opinions, judgements

    New Auto-Interp
    Negative Logits
     Continental
    -0.52
     continental
    -0.48
    Portail
    -0.47
     shir
    -0.47
    continental
    -0.46
     approximation
    -0.46
     regional
    -0.46
     lyre
    -0.46
     runnable
    -0.45
     cfg
    -0.45
    POSITIVE LOGITS
    InjectAttribute
    0.69
    rungsseite
    0.65
     récente
    0.63
     épaules
    0.62
     jouets
    0.61
     définiti
    0.58
     récents
    0.58
     виправивши
    0.57
     Italij
    0.57
     balade
    0.57
    Act Density 0.002%

    No Known Activations