INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     ruler
    -0.08
     Mockito
    -0.08
     rulers
    -0.08
     sarcast
    -0.08
     machining
    -0.08
     MACH
    -0.08
     relat
    -0.08
     wizard
    -0.08
     imperson
    -0.08
     conspir
    -0.08
    POSITIVE LOGITS
     soccer
    0.11
     Soccer
    0.10
     goalie
    0.09
     yoga
    0.09
     cannabino
    0.08
     FIFA
    0.08
    Denver
    0.08
    Hybrid
    0.08
     Kevin
    0.08
     pesto
    0.08
    Act Density 0.030%

    No Known Activations