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

    Neuronpedia

    INDEX
    Explanations

    references to official entities or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "official."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.94
    esville
    -0.89
    ocene
    -0.88
    ï¸
    -0.86
    xual
    -0.78
    icides
    -0.77
    arcity
    -0.76
    avery
    -0.76
    pecting
    -0.75
    chers
    -0.73
    POSITIVE LOGITS
     sanctioned
    0.89
     repositories
    0.80
     official
    0.80
     unofficial
    0.77
    dom
    0.77
     spokes
    0.76
     announcement
    0.76
     confirmation
    0.74
     documentation
    0.73
     unification
    0.73
    Act Density 0.021%

    No Known Activations