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

    Neuronpedia

    INDEX
    Explanations

    mentions of minority groups or minority-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to minority populations and issues related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.95
    DCS
    -0.79
    hran
    -0.77
    Closure
    -0.75
    rence
    -0.73
    lov
    -0.72
    earchers
    -0.72
    raltar
    -0.72
    atche
    -0.70
    ============
    -0.70
    POSITIVE LOGITS
     outreach
    0.86
     populations
    0.84
     minority
    0.84
     viewpoints
    0.84
     voices
    0.82
     groups
    0.81
     sects
    0.81
     communities
    0.80
     opinion
    0.79
     faiths
    0.78
    Act Density 0.028%

    No Known Activations