INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Yo
    -0.07
     Holl
    -0.07
     dalla
    -0.07
    Yo
    -0.07
    arlo
    -0.07
     perfor
    -0.07
     Kendall
    -0.07
     Silicon
    -0.07
    389
    -0.07
     flo
    -0.07
    POSITIVE LOGITS
     ancient
    0.13
     Ancient
    0.11
    libc
    0.08
    Anc
    0.08
     anc
    0.08
     древ
    0.07
    0.07
     Anc
    0.07
     antiqu
    0.07
    0.06
    Act Density 0.006%

    No Known Activations