INDEX
    Explanations

    personal names, particularly the first name "Tom" and surnames that follow it.

    New Auto-Interp
    Negative Logits
     PeEnEo
    -0.50
    OrNil
    -0.50
     שוליים
    -0.45
    :✨
    -0.42
     AppCompatTheme
    -0.41
    RenderAtEndOf
    -0.40
    -0.39
     fotografico
    -0.38
    Microkernel
    -0.37
     вікісторінку
    -0.37
    POSITIVE LOGITS
    Tom
    0.84
     Tom
    0.78
     tom
    0.74
     TOM
    0.62
    TOM
    0.60
    tom
    0.57
     Том
    0.54
    トム
    0.53
     Tomas
    0.52
     insuffisamment
    0.52
    Act Density 0.066%

    No Known Activations