INDEX
    Explanations

    emotional expressions and statements of feeling

    New Auto-Interp
    Negative Logits
    igham
    -0.17
    eldom
    -0.15
    eter
    -0.14
     ones
    -0.14
    licht
    -0.14
     Bảo
    -0.14
    uya
    -0.13
    oppers
    -0.13
    rique
    -0.13
    alog
    -0.13
    POSITIVE LOGITS
    IOC
    0.17
    mtree
    0.17
    APS
    0.15
     Michaels
    0.14
    olls
    0.14
    ê¼
    0.14
    .setInput
    0.14
    DDS
    0.14
    readcr
    0.14
    onian
    0.14
    Act Density 0.092%

    No Known Activations