INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     twelve
    -0.07
    .canvas
    -0.07
     capitalize
    -0.07
    -wheel
    -0.07
     mathematics
    -0.06
     nouvel
    -0.06
     modal
    -0.06
     marble
    -0.06
    rodu
    -0.06
    alore
    -0.06
    POSITIVE LOGITS
     infection
    0.16
     infections
    0.13
     infect
    0.10
    fection
    0.09
     infected
    0.09
     It
    0.08
     Infect
    0.08
    It
    0.07
     it
    0.07
    0.07
    Act Density 0.014%

    No Known Activations