INDEX
    Explanations

    concepts related to social acceptance and identity in the context of LGBTQ+ issues

    New Auto-Interp
    Negative Logits
    geben
    -0.15
    éĤ¦
    -0.14
    urations
    -0.14
    ãĥ¼ãĥľ
    -0.14
    æ¬
    -0.14
     november
    -0.14
    Vectorizer
    -0.14
    å½
    -0.13
    iasi
    -0.13
    uxtap
    -0.13
    POSITIVE LOGITS
    ocard
    0.14
    lier
    0.14
    avin
    0.13
    ounder
    0.13
    nik
    0.13
     Record
    0.13
     sounding
    0.12
    adic
    0.12
     gas
    0.12
    eder
    0.12
    Act Density 1.082%

    No Known Activations