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

    Neuronpedia

    INDEX
    Explanations

    references to food items and menus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
     mármol
    -0.57
     fieltro
    -0.55
     plomo
    -0.54
    Bronnen
    -0.54
     cucchiai
    -0.52
     hábiles
    -0.52
     cromado
    -0.52
     ceinture
    -0.52
     desmotivaciones
    -0.52
    POSITIVE LOGITS
     pizza
    1.36
     burgers
    1.25
     pizzas
    1.20
     hamburgers
    1.18
     pasta
    1.16
     burger
    1.13
     tacos
    1.13
     spaghetti
    1.13
     pancakes
    1.13
     lasagna
    1.09
    Act Density 0.384%

    No Known Activations