INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     democratic
    -0.08
     agriculture
    -0.08
    washing
    -0.08
    atelier
    -0.08
     '+
    -0.08
     Elections
    -0.07
    -0.07
    washed
    -0.07
     victories
    -0.07
     greenhouse
    -0.07
    POSITIVE LOGITS
    Intersect
    0.10
    .fecha
    0.08
    unks
    0.08
     incomparable
    0.08
    (rect
    0.08
     niece
    0.08
     Cartesian
    0.07
    quare
    0.07
    _
    0.07
    ulta
    0.07
    Act Density 0.010%

    No Known Activations