INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Дереккөздер
    -0.65
     Monfieur
    -0.64
     himſelf
    -0.61
     myſelf
    -0.59
     fevere
    -0.58
     Xunit
    -0.58
     dAtA
    -0.57
     OpenStreetMap
    -0.56
     themſelves
    -0.56
    instagram
    -0.55
    POSITIVE LOGITS
    rrggbb
    0.68
    xase
    0.55
    MigrationBuilder
    0.55
    Vidite
    0.55
    
    0.54
    Cyfeiriadau
    0.52
     pubs
    0.52
     referenties
    0.52
    Pubs
    0.51
    leby
    0.51
    Act Density 0.222%

    No Known Activations