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

    Neuronpedia

    INDEX
    Explanations

    mentions of conservatives

    oai_token-act-pair · gpt-3.5-turbo

    references to conservatives and discussions involving their views and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fleet
    -0.73
    amaz
    -0.73
    upon
    -0.71
    WAY
    -0.69
    Coach
    -0.68
    ãĤ¨ãĥ«
    -0.68
     Yak
    -0.65
    BY
    -0.64
    chest
    -0.64
     Marathon
    -0.64
    POSITIVE LOGITS
    ervative
    1.12
    ervatives
    1.10
    atism
    0.94
     conservatives
    0.87
     radicals
    0.84
     orthodoxy
    0.80
     thinkers
    0.79
     Protestants
    0.76
     buffs
    0.76
     popul
    0.74
    Act Density 0.010%

    No Known Activations