INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    annel
    -0.08
     Leidenschaft
    -0.08
    柴油
    -0.08
     לפי
    -0.08
     בהר
    -0.07
     sluggish
    -0.07
     cannabidiol
    -0.07
     catastrophic
    -0.07
     Struct
    -0.07
    -0.07
    POSITIVE LOGITS
     cheek
    0.09
     UFO
    0.09
    0.09
     smile
    0.09
    0.08
     cameo
    0.08
     airplane
    0.08
     mắt
    0.08
     smiles
    0.08
     wink
    0.08
    Act Density 0.012%

    No Known Activations