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

    Neuronpedia

    INDEX
    Explanations

    references to wealth or wealthy individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth and wealthy individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.80
     Airl
    -0.79
    yrinth
    -0.78
    PRESS
    -0.75
    DOC
    -0.74
    shows
    -0.72
    uberty
    -0.71
    WAYS
    -0.69
    bsp
    -0.68
    pty
    -0.67
    POSITIVE LOGITS
     earners
    1.06
     Asians
    0.88
     donors
    0.86
     landowners
    0.82
     richer
    0.81
    lier
    0.80
     wealthier
    0.80
     elites
    0.79
     citiz
    0.79
     Institution
    0.79
    Act Density 0.026%

    No Known Activations