INDEX
    Explanations

    Running distances

    New Auto-Interp
    Negative Logits
     generale
    -0.08
     geral
    -0.08
    .General
    -0.08
     üld
    -0.08
    ף
    -0.08
    uvo
    -0.08
    ajya
    -0.08
    ,v
    -0.08
    ágina
    -0.08
     kandi
    -0.08
    POSITIVE LOGITS
     Booth
    0.08
    щит
    0.07
     heure
    0.07
    stå
    0.07
     equivalent
    0.07
     Ш
    0.07
    (ST
    0.07
     pup
    0.07
     inspiring
    0.07
     shi
    0.07
    Act Density 0.005%

    No Known Activations