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

    Neuronpedia

    INDEX
    Explanations

    words related to various forms and aspects of oppression

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oppression and marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.69
    ature
    -0.69
    ãĥ¥
    -0.66
    OTAL
    -0.66
    maxwell
    -0.66
    wcsstore
    -0.64
    Interstitial
    -0.64
    natureconservancy
    -0.64
    club
    -0.62
    orah
    -0.62
    POSITIVE LOGITS
     minorities
    0.90
     oppressed
    0.83
     marginalized
    0.81
     oppression
    0.80
     LGBTQ
    0.78
     Territories
    0.77
     Africans
    0.76
     proletariat
    0.74
     Peoples
    0.74
     oppress
    0.72
    Act Density 0.128%

    No Known Activations