INDEX
    Explanations

    expressions of feeling or emotional states

    New Auto-Interp
    Negative Logits
    acades
    -0.16
    efs
    -0.16
    ese
    -0.15
    ependency
    -0.15
    bes
    -0.14
    esktop
    -0.14
    emento
    -0.14
    icerca
    -0.14
    ktop
    -0.14
    PPER
    -0.14
    POSITIVE LOGITS
    lessly
    0.21
    /sm
    0.16
     gì
    0.16
    IPA
    0.15
    419
    0.15
    inspace
    0.15
     ÑģебÑı
    0.14
    431
    0.14
    cher
    0.14
    ledged
    0.14
    Act Density 0.066%

    No Known Activations