INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Bill
    -0.08
    umik
    -0.08
    um
    -0.08
    Municip
    -0.08
     somit
    -0.07
    Um
    -0.07
    Bill
    -0.07
     Cherry
    -0.07
    LAS
    -0.07
    LM
    -0.07
    POSITIVE LOGITS
     infatti
    0.08
    0.07
     justement
    0.07
    ijuana
    0.07
    كانية
    0.07
     fél
    0.07
    可是
    0.07
     wyjątk
    0.07
     Phillips
    0.07
     too
    0.07
    Act Density 0.626%

    No Known Activations