INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Wherever
    -0.08
    rgba
    -0.08
     Highland
    -0.08
     Separator
    -0.08
     marina
    -0.08
     Better
    -0.07
     Kon
    -0.07
    =temp
    -0.07
    temp
    -0.07
    ape
    -0.07
    POSITIVE LOGITS
     хочет
    0.11
     wants
    0.11
     wanting
    0.11
     يريد
    0.10
     quiere
    0.10
     Wants
    0.10
     querendo
    0.09
     רוצה
    0.09
    さん
    0.09
     want
    0.09
    Act Density 0.011%

    No Known Activations