INDEX
    Explanations

    expressions of emotional resilience and pretense under challenging circumstances

    New Auto-Interp
    Negative Logits
    .calls
    -0.16
    DOB
    -0.15
    stub
    -0.15
    Interceptor
    -0.15
    opus
    -0.14
    Owned
    -0.14
    raquo
    -0.14
    crast
    -0.13
    /options
    -0.13
    iah
    -0.13
    POSITIVE LOGITS
     outward
    0.22
     smile
    0.21
     smiles
    0.21
     masking
    0.21
     vene
    0.20
    mask
    0.20
     faç
    0.19
     masks
    0.19
     mask
    0.19
     smiling
    0.18
    Act Density 0.187%

    No Known Activations