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

    Neuronpedia

    INDEX
    Explanations

    mentions of different nationalities or political affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities and ethnicities, particularly in the context of American and Middle Eastern identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ologies
    -1.03
    bows
    -1.02
    ravings
    -1.02
    ories
    -1.00
    rils
    -0.92
    acies
    -0.91
    abilities
    -0.91
    encies
    -0.90
    onies
    -0.88
    isites
    -0.87
    POSITIVE LOGITS
     who
    1.09
     citizen
    1.07
     politician
    1.03
     woman
    1.01
     colleague
    1.00
     traveler
    1.00
     thinker
    0.98
     traveller
    0.96
     journalist
    0.95
     believer
    0.94
    Act Density 0.260%

    No Known Activations