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

    Neuronpedia

    INDEX
    Explanations

    references to wealth and economic concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth and its distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¦
    -0.79
     externalToEVAOnly
    -0.72
    WAYS
    -0.71
    ²¾
    -0.71
    Earth
    -0.68
    £ı
    -0.66
    dq
    -0.65
    cers
    -0.65
    WAY
    -0.65
    ROR
    -0.64
    POSITIVE LOGITS
     wealth
    1.04
     inequality
    0.98
     holdings
    0.97
     disparity
    0.96
     redistribution
    0.95
     accumulation
    0.94
     amassed
    0.93
     accumulated
    0.89
     disparities
    0.86
     trove
    0.82
    Act Density 0.024%

    No Known Activations