INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    dy
    -0.08
     Fran
    -0.07
    pile
    -0.07
    ila
    -0.07
     Girona
    -0.07
    Kr
    -0.07
    dib
    -0.07
    pod
    -0.07
     gover
    -0.07
     ar
    -0.07
    POSITIVE LOGITS
     cement
    0.08
     rivers
    0.08
     Holy
    0.07
     '.$
    0.07
     egg
    0.07
    Holy
    0.07
    0.07
    she
    0.07
     iron
    0.07
    0.07
    Act Density 0.001%

    No Known Activations