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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or addresses

    oai_token-act-pair · gpt-3.5-turbo

    locations and specific addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HTML
    -0.74
    hop
    -0.68
    HTTP
    -0.66
     benefited
    -0.66
    film
    -0.65
    hops
    -0.64
     brushing
    -0.63
    METHOD
    -0.63
    tools
    -0.62
    biased
    -0.62
    POSITIVE LOGITS
    rium
    1.26
     Mile
    0.97
    las
    0.96
     dusk
    0.94
    hens
    0.91
     sunset
    0.85
     least
    0.84
     Ft
    0.84
     noon
    0.81
     Sunset
    0.81
    Act Density 0.107%

    No Known Activations