INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bell
    -0.09
     vestir
    -0.08
    -0.08
    beratung
    -0.08
     avenues
    -0.07
     hey
    -0.07
     courage
    -0.07
    กำ
    -0.07
     willingness
    -0.07
    -0.07
    POSITIVE LOGITS
    0.09
     intimately
    0.09
     lèvres
    0.08
    0.08
    0.08
     accomplished
    0.08
     nhau
    0.07
    ότε
    0.07
     kissing
    0.07
    0.07
    Act Density 0.010%

    No Known Activations