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

    Neuronpedia

    INDEX
    Explanations

    references to specific snack foods or candies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .tom
    -0.18
    bé
    -0.17
    ãĥ¥
    -0.16
     pigeon
    -0.16
     potatoes
    -0.16
    åľ°ä¸ĭ
    -0.16
     tomatoes
    -0.16
     Governors
    -0.15
     gravy
    -0.15
    Soup
    -0.15
    POSITIVE LOGITS
     candy
    0.28
     candies
    0.26
     nou
    0.24
     brittle
    0.23
     marsh
    0.21
     treat
    0.21
     Candy
    0.21
     cand
    0.20
     chew
    0.20
     treats
    0.20
    Act Density 0.075%

    No Known Activations