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

    Neuronpedia

    INDEX
    Explanations

    references to dining-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to dining and dining rooms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Static
    -0.70
     Virus
    -0.68
    rar
    -0.65
    acles
    -0.64
     Fundamental
    -0.64
     Prototype
    -0.62
    onen
    -0.62
    Hero
    -0.62
    Project
    -0.61
    MH
    -0.61
    POSITIVE LOGITS
     dining
    3.69
     eating
    1.54
     culinary
    1.54
     meal
    1.52
     restaurant
    1.49
     dinner
    1.46
     meals
    1.46
     restaurants
    1.45
     seating
    1.44
     diner
    1.42
    Act Density 0.008%

    No Known Activations