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

    Neuronpedia

    INDEX
    Explanations

    references to food and dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frazer
    -0.68
     hexagon
    -0.60
    kolen
    -0.58
    ntgen
    -0.58
    itisation
    -0.57
    ództ
    -0.57
     Myers
    -0.57
     Over
    -0.57
    ValueStyle
    -0.56
    setLoading
    -0.56
    POSITIVE LOGITS
     dish
    2.03
     dishes
    1.98
     Dish
    1.94
     Dishes
    1.89
     DISH
    1.80
    Dish
    1.80
    dish
    1.68
    Dishes
    1.67
    dishes
    1.55
     Sputnik
    1.01
    Act Density 0.128%

    No Known Activations