INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bun
    -0.08
    changes
    -0.07
    -effects
    -0.07
     Lip
    -0.07
     Molina
    -0.07
    _hand
    -0.07
     progression
    -0.07
    -0.07
     changes
    -0.07
     causal
    -0.07
    POSITIVE LOGITS
    Prefs
    0.09
    .Test
    0.08
    .mapper
    0.08
     rex
    0.08
    Fp
    0.08
     Sicily
    0.08
    .parameter
    0.07
     авт
    0.07
     STORY
    0.07
     complains
    0.07
    Act Density 0.001%

    No Known Activations