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

    Neuronpedia

    INDEX
    Explanations

    political voting actions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "vote for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scope
    -0.79
    urst
    -0.78
    clair
    -0.78
    illin
    -0.77
    pour
    -0.74
    oller
    -0.74
    edin
    -0.71
    prov
    -0.70
    hew
    -0.70
    Wars
    -0.69
    POSITIVE LOGITS
     starters
    0.82
     example
    0.82
    gotten
    0.82
     reelection
    0.80
    bidden
    0.77
     captcha
    0.76
     whatever
    0.76
     Hillary
    0.74
     awhile
    0.72
     hire
    0.71
    Act Density 0.087%

    No Known Activations