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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the article "the" and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McKenzie
    -0.66
     Reloaded
    -0.65
     Domain
    -0.64
     Enterprise
    -0.63
     Fraser
    -0.63
    warm
    -0.62
    DERR
    -0.61
     Wonderland
    -0.60
     Gutenberg
    -0.60
     proxies
    -0.59
    POSITIVE LOGITS
    onym
    1.00
    ocrat
    0.90
    cery
    0.88
    onymous
    0.87
    phony
    0.87
    phy
    0.86
    odic
    0.84
    opol
    0.84
    cer
    0.83
    swer
    0.82
    Act Density 0.097%

    No Known Activations