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

    Neuronpedia

    INDEX
    Explanations

    names, titles, and phrases related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent political figures and strategists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.70
     Chilean
    -0.68
    EVA
    -0.68
     captcha
    -0.67
     Jagu
    -0.66
    ivity
    -0.62
    eon
    -0.62
    phis
    -0.62
    proof
    -0.62
    ires
    -0.62
    POSITIVE LOGITS
     Bannon
    0.86
    fried
    0.82
    hattan
    0.81
    rosso
    0.75
    annon
    0.74
    bara
    0.72
    andowski
    0.72
    iances
    0.69
    hammer
    0.68
    bach
    0.68
    Act Density 0.055%

    No Known Activations