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

    Neuronpedia

    INDEX
    Explanations

    mentions of high-ranking individuals, particularly those mentioned as "senior"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in senior positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.77
    doors
    -0.72
    pel
    -0.71
     Hispan
    -0.70
    ãĥķãĤ©
    -0.67
    AUT
    -0.66
    plex
    -0.64
    igor
    -0.64
    laws
    -0.63
    aster
    -0.62
    POSITIVE LOGITS
     citiz
    0.95
    iating
    0.90
     aide
    0.87
    iors
    0.85
    iate
    0.85
    ially
    0.83
    iates
    0.81
    doms
    0.78
    ity
    0.78
     adviser
    0.75
    Act Density 0.015%

    No Known Activations