INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     большой
    -0.07
     warmth
    -0.07
    -light
    -0.07
     light
    -0.07
     Ballard
    -0.07
    _converter
    -0.07
     touch
    -0.07
    requency
    -0.07
     camera
    -0.07
    _UNIQUE
    -0.07
    POSITIVE LOGITS
     fol
    0.13
     Fol
    0.11
    fol
    0.09
     foliage
    0.09
    FormItem
    0.07
    scri
    0.07
     Pag
    0.07
    	
    ↵	
    ↵
    0.07
    olio
    0.07
     dated
    0.07
    Act Density 0.005%

    No Known Activations