INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     duele
    -0.50
    achte
    -0.49
    Vaata
    -0.48
     Semoga
    -0.48
     linken
    -0.47
    Vicente
    -0.47
    Blame
    -0.47
    Indie
    -0.47
     Haye
    -0.47
    Kick
    -0.47
    POSITIVE LOGITS
     enormous
    1.16
    ormous
    1.10
     enormously
    1.02
     enorme
    0.77
     enormes
    0.73
     enorm
    0.71
     gigantic
    0.63
     extraordinarily
    0.63
     tremendous
    0.57
     extraordinary
    0.56
    Act Density 0.004%

    No Known Activations