INDEX
    Explanations

    supporters/fans/crowd

    New Auto-Interp
    Negative Logits
    ilia
    -0.08
    abilia
    -0.08
    ­ti
    -0.08
    weich
    -0.08
     在
    -0.08
     Pop
    -0.08
     Gip
    -0.07
     tete
    -0.07
    ีน
    -0.07
    -0.07
    POSITIVE LOGITS
     owes
    0.09
     inorder
    0.08
     dissatisfied
    0.08
     animation
    0.08
     hearth
    0.08
     boos
    0.08
     simultaneously
    0.08
     Concern
    0.08
     daya
    0.08
     lime
    0.08
    Act Density 0.036%

    No Known Activations