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

    Neuronpedia

    INDEX
    Explanations

    nationalities or origins of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities or ethnic identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nels
    -0.78
    uador
    -0.77
     oneself
    -0.72
     Canaver
    -0.69
    urtles
    -0.68
    ]'
    -0.67
    edia
    -0.67
    ieve
    -0.66
    nell
    -0.65
    aples
    -0.65
    POSITIVE LOGITS
     counterparts
    1.59
     counterpart
    1.58
     brethren
    1.23
     cousin
    1.09
     colleague
    1.07
     cousins
    1.07
     companion
    1.03
     namesake
    1.03
     colleagues
    1.01
     holdings
    0.99
    Act Density 0.361%

    No Known Activations