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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of academics and their fields of expertise

    oai_token-act-pair · gpt-3.5-turbo

    references to mathematicians, philosophers, and historians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pradesh
    -0.89
    ibaba
    -0.79
    payer
    -0.69
    kee
    -0.69
    estate
    -0.68
     Territories
    -0.68
    eals
    -0.66
    loaded
    -0.64
    kus
    -0.63
     quo
    -0.63
    POSITIVE LOGITS
     extraord
    1.08
     laureate
    1.01
     who
    0.95
     Stephen
    0.80
    esses
    0.80
    who
    0.80
    Artist
    0.79
     Richard
    0.78
     Natalie
    0.78
    ically
    0.76
    Act Density 0.071%

    No Known Activations