INDEX
    Explanations

    casual and informal expressions related to personal experiences and anecdotes

    New Auto-Interp
    Negative Logits
    ken
    -0.16
    umo
    -0.15
    êu
    -0.15
    živ
    -0.15
    för
    -0.14
     damer
    -0.14
    ouri
    -0.14
     addCriterion
    -0.14
    zy
    -0.13
    lek
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥª
    0.18
    asse
    0.15
    onto
    0.15
    çĿ£
    0.15
     onto
    0.14
     Occ
    0.14
    ваниÑı
    0.14
     into
    0.14
     with
    0.14
     idea
    0.13
    Act Density 0.470%

    No Known Activations