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

    Neuronpedia

    INDEX
    Explanations

    proper names, likely of people in politics or news

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bahá
    -0.74
     Siber
    -0.71
    âĸĪâĸĪâĸĪâĸĪ
    -0.69
     Ryder
    -0.66
    acters
    -0.65
     Siberian
    -0.64
    76561
    -0.63
    Lex
    -0.63
     Memphis
    -0.62
    Rus
    -0.62
    POSITIVE LOGITS
     appoint
    1.12
     supporters
    1.09
     campaigned
    1.04
     appointed
    1.03
     administration
    1.00
     vetoed
    0.96
     aides
    0.95
     supporter
    0.95
     presided
    0.94
    ozy
    0.93
    Act Density 0.219%

    No Known Activations