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

    Neuronpedia

    INDEX
    Explanations

    mentions of different cultures and civilizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various cultures and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outine
    -0.78
     spot
    -0.75
     facility
    -0.75
     position
    -0.73
     affair
    -0.72
     company
    -0.69
     racket
    -0.67
     house
    -0.67
     mansion
    -0.65
     seat
    -0.65
    POSITIVE LOGITS
     cultures
    2.68
     civilizations
    2.22
     religions
    2.09
     faiths
    2.08
     societies
    2.01
     empires
    1.79
     democracies
    1.70
     climates
    1.67
     continents
    1.62
     eras
    1.62
    Act Density 0.048%

    No Known Activations