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

    Neuronpedia

    INDEX
    Explanations

    phrases related to marginalized groups, social justice, and diversity

    oai_token-act-pair · gpt-3.5-turbo

    references to marginalized groups and discussions about inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nut
    -0.69
    nit
    -0.68
    tun
    -0.65
    quickShipAvailable
    -0.65
     Majesty
    -0.64
    aic
    -0.63
    inventoryQuantity
    -0.63
    orius
    -0.63
    LOCK
    -0.62
    });
    -0.62
    POSITIVE LOGITS
     residing
    1.05
    hood
    1.03
     living
    1.01
     oppressed
    0.95
     disproportionately
    0.93
     marrying
    0.89
     marginalized
    0.88
     experiencing
    0.87
     disproportion
    0.87
     privilege
    0.85
    Act Density 0.249%

    No Known Activations