INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    egg
    -0.08
     eyebrow
    -0.07
    IRONMENT
    -0.07
    olate
    -0.07
     snippet
    -0.07
     elaborar
    -0.07
    putate
    -0.07
    landing
    -0.07
     ingresar
    -0.07
    aur
    -0.07
    POSITIVE LOGITS
     chacun
    0.08
     Hel
    0.07
    ír
    0.07
    ిక
    0.07
    мен
    0.07
     habits
    0.07
     Minute
    0.07
     hobbies
    0.07
    (item
    0.07
     Herr
    0.07
    Act Density 0.013%

    No Known Activations