INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     miller
    -0.78
    -0.74
    -0.72
     Miller
    -0.71
    -0.70
     edilir
    -0.65
    itura
    -0.65
    entlig
    -0.65
    dialog
    -0.64
     Municipio
    -0.64
    POSITIVE LOGITS
     selector
    1.21
    selector
    1.14
    Selector
    1.11
     Selector
    1.05
    SEL
    1.00
    :@
    1.00
    (@
    0.96
    Sel
    0.95
     selectors
    0.95
     sel
    0.88
    Act Density 0.019%

    No Known Activations