INDEX
    Explanations

    references to personal identity issues and self-esteem

    New Auto-Interp
    Negative Logits
    oman
    -0.16
    olis
    -0.14
    Enumerator
    -0.14
     Ù¾ÛĮÙĪÙĨد
    -0.14
     promise
    -0.13
    KS
    -0.13
    olo
    -0.13
     mil
    -0.13
     networks
    -0.13
    acked
    -0.13
    POSITIVE LOGITS
    loy
    0.17
    ä½ĵèĤ²
    0.15
    273
    0.15
     tÃŃn
    0.14
    zsche
    0.14
    pty
    0.14
    ¶Į
    0.14
    760
    0.14
    uby
    0.14
    createView
    0.14
    Act Density 0.036%

    No Known Activations