INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Mutex
    -0.09
    Bag
    -0.08
    Dirty
    -0.08
    uega
    -0.08
    Last
    -0.08
    Apply
    -0.08
    Ghost
    -0.08
    ghost
    -0.08
    	initialize
    -0.07
    gate
    -0.07
    POSITIVE LOGITS
     cosine
    0.09
     최대
    0.09
     verão
    0.09
     verano
    0.08
     maximize
    0.08
     cosy
    0.08
     autumn
    0.08
     summer
    0.08
     farther
    0.08
     inverno
    0.08
    Act Density 0.008%

    No Known Activations