INDEX
    Explanations

    emotional expressions and their descriptions on faces

    New Auto-Interp
    Negative Logits
    alles
    -0.15
     Hindered
    -0.15
    elda
    -0.15
    atars
    -0.14
    atar
    -0.14
    åı°
    -0.14
    thers
    -0.14
     rè
    -0.14
    æĦ¿
    -0.14
    pher
    -0.13
    POSITIVE LOGITS
     facial
    0.20
     expression
    0.19
    表æĥħ
    0.18
     expressions
    0.18
     faces
    0.17
    -expression
    0.16
    imenti
    0.16
     Expression
    0.16
    cape
    0.16
    Expressions
    0.15
    Act Density 0.163%

    No Known Activations