INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Bed
    -0.09
    Vis
    -0.08
    Patch
    -0.07
    itai
    -0.07
     souff
    -0.07
    USH
    -0.07
    Ansi
    -0.07
     eclipse
    -0.07
    Cob
    -0.07
    -0.07
    POSITIVE LOGITS
     onwards
    0.09
     jobs
    0.08
     паміж
    0.08
     ജോ
    0.08
     ശേഷം
    0.08
     দৈ
    0.07
     ts
    0.07
     medzi
    0.07
     psik
    0.07
     Next
    0.07
    Act Density 0.005%

    No Known Activations