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

    Neuronpedia

    INDEX
    Explanations

    mentions of ingredients in recipes or food-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to ingredients in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arton
    -0.75
     Winds
    -0.74
    geons
    -0.69
    roe
    -0.67
     Gib
    -0.66
    ¥µ
    -0.65
    udeb
    -0.64
     Gri
    -0.64
    ilege
    -0.64
    awar
    -0.64
    POSITIVE LOGITS
     ingredients
    1.24
     ingredient
    1.12
    Ingredients
    0.95
     additives
    0.91
     ingred
    0.89
     suppliers
    0.89
     oils
    0.83
     kosher
    0.83
    cream
    0.82
     supplier
    0.81
    Act Density 0.038%

    No Known Activations