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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures, especially Chris Christie

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.80
    ury
    -0.73
    eon
    -0.73
    ulhu
    -0.73
    variable
    -0.72
    ivity
    -0.70
    ories
    -0.70
    omaly
    -0.67
     Corpus
    -0.66
    omething
    -0.65
    POSITIVE LOGITS
     aides
    1.12
     vetoed
    1.09
     aide
    1.02
     appoint
    1.01
     confid
    0.96
     Kasich
    0.91
     supporters
    0.91
     campaigned
    0.90
     Huckabee
    0.90
     pard
    0.89
    Act Density 0.066%

    No Known Activations