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

    Neuronpedia

    INDEX
    Explanations

    statistical data and economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behaviors
    -0.19
     unfavorable
    -0.16
     flavors
    -0.16
    -colored
    -0.16
     favor
    -0.16
    ingu
    -0.15
     flavored
    -0.15
     unfavor
    -0.15
     colors
    -0.15
     civilizations
    -0.15
    POSITIVE LOGITS
     capitalists
    0.20
     capitalist
    0.20
     imperial
    0.19
     bourgeois
    0.19
     workers
    0.19
     bosses
    0.18
     Trotsky
    0.17
     Workers
    0.16
     ha
    0.16
     capital
    0.15
    Act Density 0.002%

    No Known Activations