INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ổng
    -0.07
     Rach
    -0.06
    -0.06
     Maharashtra
    -0.06
     Mais
    -0.06
    ioxid
    -0.06
    есь
    -0.06
     Nancy
    -0.06
     bland
    -0.06
    amb
    -0.06
    POSITIVE LOGITS
     figures
    0.16
     figure
    0.16
    -figure
    0.11
    figures
    0.11
     figura
    0.11
     Figures
    0.11
    figure
    0.10
    Fig
    0.10
     fig
    0.10
    (fig
    0.10
    Act Density 0.013%

    No Known Activations