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

    Neuronpedia

    INDEX
    Explanations

    references to or mentions of different types of bowls

    oai_token-act-pair · gpt-3.5-turbo

    references to bowls and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.83
    bourg
    -0.66
     UTC
    -0.61
     Intercept
    -0.60
     Dame
    -0.60
     Phantom
    -0.60
     Greenwich
    -0.59
     Benson
    -0.58
     Anarchy
    -0.58
     Assass
    -0.57
    POSITIVE LOGITS
    pipe
    1.06
    ers
    1.00
    lain
    0.97
    ful
    0.97
    cup
    0.92
     bowl
    0.89
    pour
    0.88
    washer
    0.85
    cake
    0.85
    mates
    0.83
    Act Density 0.037%

    No Known Activations