INDEX
    Explanations

    phrases highlighting education, social class expectations, and societal norms regarding relationships

    New Auto-Interp
    Negative Logits
     otherwise
    -0.17
     overall
    -0.16
     crucial
    -0.15
     critical
    -0.14
    ibli
    -0.14
     sourcing
    -0.14
    hlen
    -0.14
     key
    -0.14
     penn
    -0.14
    ãģłãģijãģ§
    -0.14
    POSITIVE LOGITS
     modern
    0.26
     commercial
    0.25
    -commercial
    0.24
    modern
    0.23
    Modern
    0.22
     Modern
    0.21
     moderne
    0.21
     comercial
    0.21
    commercial
    0.20
     ÑģÑĥÑĩаÑģ
    0.20
    Act Density 0.025%

    No Known Activations