INDEX
    Explanations

    expressions of disappointment or complaints about films

    New Auto-Interp
    Negative Logits
    imeline
    -0.19
    udden
    -0.15
    aniem
    -0.15
    .Guna
    -0.15
    kiem
    -0.15
    çĶ
    -0.15
    dera
    -0.14
    appe
    -0.14
    ideshow
    -0.14
    casts
    -0.14
    POSITIVE LOGITS
    ledo
    0.16
    olor
    0.14
    elle
    0.14
    eward
    0.14
     Leer
    0.14
    Performance
    0.13
     Klopp
    0.13
    illions
    0.13
     sum
    0.13
    upid
    0.13
    Act Density 0.179%

    No Known Activations