INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     dejo
    -0.08
    Bron
    -0.08
    -0.08
    Usb
    -0.08
    IMAL
    -0.07
    olas
    -0.07
    onate
    -0.07
    Paso
    -0.07
    Double
    -0.07
    Sword
    -0.07
    POSITIVE LOGITS
     incomparable
    0.15
     fundamentally
    0.11
     comparação
    0.10
     apples
    0.10
    比较
    0.10
     incompatible
    0.10
     comparison
    0.10
     Comparable
    0.10
     compar
    0.10
     comparar
    0.10
    Act Density 0.024%

    No Known Activations