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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "Hay" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Hay or variations of that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urally
    -0.88
    andestine
    -0.85
    inyl
    -0.82
    ortium
    -0.80
     Mayhem
    -0.72
    ysis
    -0.71
    wcs
    -0.69
     restrooms
    -0.69
     restroom
    -0.68
    ossibility
    -0.68
    POSITIVE LOGITS
    wire
    1.09
    stack
    1.04
    nes
    0.91
    leigh
    0.90
    elin
    0.89
    maker
    0.88
    ley
    0.87
    ashi
    0.87
    makers
    0.87
    den
    0.86
    Act Density 0.020%

    No Known Activations