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

    Neuronpedia

    INDEX
    Explanations

    references to nobility or nobleness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "noble" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.78
     Gutenberg
    -0.77
    lez
    -0.70
    artney
    -0.68
    arella
    -0.66
    aturation
    -0.65
     Ibid
    -0.64
    acea
    -0.63
    Buzz
    -0.63
    okia
    -0.62
    POSITIVE LOGITS
    men
    1.03
    minded
    0.97
    woman
    0.97
    ments
    0.94
    bour
    0.93
    bridge
    0.88
    ries
    0.87
    man
    0.87
    rie
    0.85
     pursuits
    0.77
    Act Density 0.057%

    No Known Activations