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

    Neuronpedia

    INDEX
    Explanations

    references to specific countries in the context of political events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to nationalities or ethnicities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.90
    ickle
    -0.86
    igham
    -0.84
    utherford
    -0.82
    rex
    -0.82
    allery
    -0.81
    olkien
    -0.80
    illance
    -0.80
    ifice
    -0.80
    anship
    -0.79
    POSITIVE LOGITS
    istani
    0.93
     nationals
    0.90
     Nadu
    0.88
     diplomats
    0.87
     citiz
    0.87
     nationalist
    0.85
     embassies
    0.85
    oslov
    0.82
     counterpart
    0.82
     embassy
    0.82
    Act Density 0.107%

    No Known Activations