INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     traf
    -0.08
     Leb
    -0.08
    Leb
    -0.08
     telev
    -0.08
     serais
    -0.08
     Zd
    -0.08
    usize
    -0.07
     vets
    -0.07
     NG
    -0.07
     Moderna
    -0.07
    POSITIVE LOGITS
     rowing
    0.11
    0.09
    0.09
    0.08
    0.08
     forstå
    0.08
    0.08
     तल
    0.08
     espalda
    0.08
     carriage
    0.08
    Act Density 0.004%

    No Known Activations