INDEX
    Explanations

    Kevin followed by a surname

    New Auto-Interp
    Negative Logits
     eject
    -0.93
    -0.92
     rodilla
    -0.91
    ↵↵
    -0.90
     statements
    -0.86
    -0.85
    后来
    -0.82
    unjuk
    -0.82
     deberán
    -0.82
     governments
    -0.81
    POSITIVE LOGITS
    1.11
     fantasia
    0.98
    according
    0.96
     essayé
    0.96
     Observe
    0.93
     celý
    0.93
    面目
    0.92
     espl
    0.92
     equipa
    0.92
    opher
    0.91
    Act Density 0.004%

    No Known Activations