INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     notion
    -0.09
     angel
    -0.08
     Katr
    -0.08
     Kabel
    -0.08
    nickname
    -0.08
     positivity
    -0.07
     stake
    -0.07
    typing
    -0.07
     hidrául
    -0.07
    ilyen
    -0.07
    POSITIVE LOGITS
    0.08
    .dictionary
    0.08
    .sha
    0.08
    .direct
    0.08
     competing
    0.07
    0.07
     ERR
    0.07
    reatment
    0.07
     отдел
    0.07
    CS
    0.07
    Act Density 0.000%

    No Known Activations