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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "dish"

    oai_token-act-pair · gpt-3.5-turbo

    references to dishes and dishwashers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Glob
    -0.72
     Powers
    -0.71
     Associated
    -0.68
     Fore
    -0.63
     International
    -0.63
     Kindle
    -0.62
     Pall
    -0.61
     Hammond
    -0.61
     Johann
    -0.61
     Gat
    -0.61
    POSITIVE LOGITS
    washer
    1.88
     dish
    1.31
     dishes
    1.27
    washing
    1.05
    ware
    1.01
    cake
    0.97
    cloth
    0.90
    dayName
    0.87
    bowl
    0.83
    irez
    0.80
    Act Density 0.006%

    No Known Activations