INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    pessoa
    0.41
     rumours
    0.39
     touristic
    0.38
     Erasmus
    0.38
     digitalisation
    0.38
    etty
    0.38
     doraemon
    0.37
    neighbours
    0.37
    TypeDef
    0.37
    0.37
    POSITIVE LOGITS
     Atlanta
    1.89
     Chicago
    1.84
     Seattle
    1.81
     Baltimore
    1.77
     Philadelphia
    1.76
     California
    1.71
     Florida
    1.70
    Atlanta
    1.70
     Minneapolis
    1.66
    Chicago
    1.63
    Act Density 0.011%

    No Known Activations