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

    Neuronpedia

    INDEX
    Explanations

    references to wealth, accumulation, taxation, and redistribution

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth and economic disparity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¦
    -0.77
    WAYS
    -0.74
     externalToEVAOnly
    -0.70
    cers
    -0.69
    WAY
    -0.69
    apple
    -0.67
    ROR
    -0.66
    Earth
    -0.65
    ATIONS
    -0.64
     Yel
    -0.64
    POSITIVE LOGITS
     wealth
    1.08
     inequality
    0.98
     disparity
    0.96
     holdings
    0.94
     disparities
    0.93
     accumulation
    0.90
     redistribution
    0.89
     trove
    0.85
    ocrats
    0.82
     amassed
    0.79
    Act Density 0.013%

    No Known Activations