INDEX
    Explanations

    phrases or expressions denoting social isolation or exclusion

    New Auto-Interp
    Negative Logits
    anim
    -0.18
    ]={↵
    -0.17
     migrationBuilder
    -0.16
    (æĹ¥
    -0.14
    ëŁ
    -0.14
    readystatechange
    -0.14
    ç¯Ģ
    -0.14
    ylum
    -0.14
    /stdc
    -0.14
    iek
    -0.14
    POSITIVE LOGITS
    Fonts
    0.17
    üss
    0.17
    ipo
    0.15
     اÛĮÙĨÚ©Ùĩ
    0.15
    est
    0.15
    enthal
    0.14
    aris
    0.14
    ç·
    0.14
    esta
    0.13
    edd
    0.13
    Act Density 0.009%

    No Known Activations