INDEX
    Explanations

    terms and phrases related to transgender identities and experiences

    New Auto-Interp
    Negative Logits
    chw
    -0.17
    hte
    -0.15
    sel
    -0.15
    меÑĢик
    -0.14
     LUA
    -0.14
    stras
    -0.14
    }->
    -0.14
    imity
    -0.14
    croft
    -0.13
    ounder
    -0.13
    POSITIVE LOGITS
    142
    0.16
    622
    0.15
    ufs
    0.15
     tid
    0.15
    169
    0.14
     caller
    0.14
    à¸Ńà¸Ńà¸Ļà¹Ħลà¸Ļ
    0.14
    931
    0.14
     Ting
    0.14
     wet
    0.13
    Act Density 0.010%

    No Known Activations