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

    Neuronpedia

    INDEX
    Explanations

    political affiliations of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political affiliations and the associated individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.78
    ternity
    -0.76
     Palest
    -0.74
    agy
    -0.71
     ante
    -0.71
    foundland
    -0.66
     Kinnikuman
    -0.66
    arget
    -0.64
    lla
    -0.63
     Australians
    -0.63
    POSITIVE LOGITS
    istrates
    0.93
     district
    0.78
    itol
    0.72
    hei
    0.68
    ways
    0.68
    ivan
    0.66
    ptroller
    0.66
     legislature
    0.65
    orate
    0.65
    eworks
    0.65
    Act Density 0.295%

    No Known Activations