INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    IH
    -0.08
     объ
    -0.08
     Verm
    -0.07
    -0.07
    🏻
    -0.07
     Herb
    -0.07
     Xen
    -0.07
    .equal
    -0.07
    -0.07
     Gab
    -0.07
    POSITIVE LOGITS
     operativo
    0.09
     ach
    0.09
     구축
    0.08
     hei
    0.08
     blends
    0.08
     eficaz
    0.08
     Simon
    0.08
     cul
    0.07
    atics
    0.07
     fo
    0.07
    Act Density 0.055%

    No Known Activations