INDEX
    Explanations

    names of specific actors and actresses

    New Auto-Interp
    Negative Logits
    azzi
    -0.18
    иÑĩа
    -0.17
    ivec
    -0.16
    grave
    -0.16
    ikat
    -0.14
    ãĥŃãĥ¼
    -0.14
    èįī
    -0.14
    aro
    -0.14
    audi
    -0.14
    ikh
    -0.14
    POSITIVE LOGITS
     {?>↵
    0.16
    uem
    0.15
       
    0.14
    .typ
    0.14
     provoc
    0.13
    uden
    0.13
    _vc
    0.13
    .fx
    0.13
      
    0.13
    ibile
    0.13
    Act Density 0.113%

    No Known Activations