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

    Neuronpedia

    INDEX
    Explanations

    words associated with food and recipes, particularly ingredients and cooking methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.01
    2:0.05
    3:0.41
    4:0.02
    5:0.13
    6:0.02
    7:0.04
    8:0.04
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     generational
    -2.01
    Detect
    -1.98
     Regulatory
    -1.96
     eligibility
    -1.90
     Inspect
    -1.89
    Engineers
    -1.80
     Communications
    -1.76
     Investigative
    -1.75
     criminality
    -1.75
    Public
    -1.75
    POSITIVE LOGITS
     salad
    3.04
     noodles
    2.97
     salads
    2.84
     cheese
    2.83
     curry
    2.81
     meal
    2.81
     biscuits
    2.79
     salsa
    2.78
     chocolate
    2.72
     snacks
    2.70
    Act Density 1.271%

    No Known Activations