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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    cooking actions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urance
    -0.68
    oho
    -0.66
    女
    -0.66
    xus
    -0.65
    iqueness
    -0.64
    clus
    -0.63
     guiActiveUn
    -0.62
    fax
    -0.61
    termination
    -0.61
     interoper
    -0.60
    POSITIVE LOGITS
     onions
    1.11
     rice
    1.03
     tofu
    1.01
     shrimp
    1.01
     veggies
    1.00
     pasta
    0.97
     chicken
    0.97
     vegetables
    0.95
     potatoes
    0.94
     meats
    0.94
    Act Density 0.084%

    No Known Activations