Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    adjectives related to gender, specifically "masculine" and "feminine"

    oai_token-act-pair · gpt-4-turbo

    traits, characteristics, and behaviors associated with masculinity and femininity

    oai_token-act-pair · gpt-3.5-turbo

    references to gender norms and characteristics associated with masculinity and femininity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akings
    -0.82
    Assembly
    -0.81
    Deal
    -0.78
    oulos
    -0.78
    EVA
    -0.77
    Rush
    -0.72
    EV
    -0.71
    Money
    -0.70
    BUR
    -0.68
     Bans
    -0.67
    POSITIVE LOGITS
     masculine
    1.14
     masculinity
    1.11
     mascul
    1.00
     feminine
    0.98
     femin
    0.93
     adolesc
    0.80
     hygiene
    0.80
     streng
    0.77
     pronouns
    0.77
     stereotyp
    0.76
    Act Density 0.015%

    No Known Activations