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

    Neuronpedia

    INDEX
    Explanations

    references to meals and meal services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    meal service

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     azules
    -0.54
     amarelo
    -0.53
     Griffiths
    -0.53
     amarillas
    -0.53
     white
    -0.50
     copper
    -0.49
     Fox
    -0.49
     femininas
    -0.49
     vermelho
    -0.49
     sarı
    -0.48
    POSITIVE LOGITS
    Meal
    1.08
     Meal
    1.06
     meal
    1.02
    meal
    0.98
     meals
    0.91
     Meals
    0.90
    meals
    0.85
    Meals
    0.83
    Dinner
    0.62
    dinner
    0.61
    Act Density 0.003%

    No Known Activations