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

    Neuronpedia

    INDEX
    Explanations

    references to different nations

    oai_token-act-pair · gpt-3.5-turbo

    references to countries or sovereign states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Serial
    -0.74
    washer
    -0.71
    lease
    -0.69
    abre
    -0.68
     alias
    -0.66
     Garage
    -0.66
    rette
    -0.66
    stack
    -0.63
    trap
    -0.63
    FH
    -0.61
    POSITIVE LOGITS
     nations
    3.52
     countries
    2.57
     Countries
    2.23
     Nations
    2.10
     democracies
    2.00
     nation
    1.85
     societies
    1.81
     governments
    1.78
     Governments
    1.62
     empires
    1.62
    Act Density 0.016%

    No Known Activations