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

    Neuronpedia

    INDEX
    Explanations

    words related to social justice and oppression

    oai_token-act-pair · gpt-3.5-turbo

    themes related to oppression and marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.84
    natureconservancy
    -0.77
    soType
    -0.73
    wcsstore
    -0.71
    ullivan
    -0.70
    PET
    -0.69
    sterdam
    -0.69
    sal
    -0.69
    cephal
    -0.68
    ski
    -0.68
    POSITIVE LOGITS
     marginalized
    0.89
     oppressed
    0.88
     minorities
    0.87
     disadvant
    0.87
     disproportion
    0.85
    ments
    0.81
     injust
    0.79
     Territories
    0.79
     Asians
    0.77
     disproportionately
    0.77
    Act Density 0.172%

    No Known Activations