INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    inne
    -0.06
     bow
    -0.06
     fing
    -0.06
     muff
    -0.06
     kne
    -0.06
     Cook
    -0.06
     goof
    -0.06
    てる
    -0.06
    )\↵
    -0.06
     sofa
    -0.06
    POSITIVE LOGITS
     Businesses
    0.07
     ш
    0.07
     MED
    0.06
    PGA
    0.06
    0.06
     Burma
    0.06
     NVIC
    0.06
    ۲۰۱
    0.06
    .C
    0.06
    (ctx
    0.06
    Act Density 0.046%

    No Known Activations