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

    Neuronpedia

    INDEX
    Explanations

    references to specific websites or web pages

    oai_token-act-pair · gpt-3.5-turbo

    references to official websites or pages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.75
     imperson
    -0.69
     evict
    -0.67
     someday
    -0.66
     Imran
    -0.65
     forcibly
    -0.64
    zon
    -0.64
     Qiao
    -0.62
    ictions
    -0.58
    adays
    -0.58
    POSITIVE LOGITS
     respective
    1.04
     aforementioned
    1.00
     following
    0.96
     sidebar
    0.95
     FAQ
    0.92
     menu
    0.91
     nearest
    0.89
     homepage
    0.88
     corresponding
    0.88
     appropriate
    0.88
    Act Density 0.175%

    No Known Activations