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

    Neuronpedia

    INDEX
    Explanations

    ingredients or cooking-related words in recipes

    oai_token-act-pair · gpt-3.5-turbo

    references to specific items or recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.78
    arson
    -0.74
    andum
    -0.73
    witz
    -0.71
    isms
    -0.71
    occup
    -0.69
    adata
    -0.67
    ussen
    -0.67
    lev
    -0.66
    anamo
    -0.66
    POSITIVE LOGITS
     lovely
    0.91
     guy
    0.86
     lowly
    0.85
     amazing
    0.85
     nifty
    0.83
     particular
    0.83
     gorgeous
    0.83
     handy
    0.79
     sucker
    0.78
     adorable
    0.78
    Act Density 0.219%

    No Known Activations