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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the distribution or possession of items and food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dieux
    -0.67
     rayures
    -0.64
     doigts
    -0.63
     chré
    -0.61
     égale
    -0.61
     dentes
    -0.61
     attentes
    -0.59
     sereia
    -0.59
     lèvres
    -0.59
     racines
    -0.58
    POSITIVE LOGITS
     food
    1.57
     snacks
    1.48
     refreshments
    1.32
     drinks
    1.27
     coffee
    1.26
     popcorn
    1.22
    food
    1.21
     beer
    1.20
     sandwiches
    1.17
     pizza
    1.13
    Act Density 0.489%

    No Known Activations