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

    Neuronpedia

    INDEX
    Explanations

    terms related to a specific political party (Conservative) and their actions, leaders, and policies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Conservative Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...]
    -0.76
    agram
    -0.75
    ansom
    -0.73
    ipt
    -0.73
    ipers
    -0.72
     Artemis
    -0.72
     Runes
    -0.71
     Kard
    -0.70
    olean
    -0.69
    ofi
    -0.69
    POSITIVE LOGITS
     Conservative
    1.06
     Conservatives
    0.99
    Conservative
    0.95
     Party
    0.85
    atism
    0.79
     MP
    0.75
     Coun
    0.73
     Liberal
    0.72
     Liberals
    0.70
     correctness
    0.69
    Act Density 0.008%

    No Known Activations