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

    Neuronpedia

    INDEX
    Explanations

    names, particularly "Joey" and "Monica"

    oai_token-act-pair · gpt-3.5-turbo

    names of characters in a specific narrative or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stroke
    -0.90
    maid
    -0.88
    fitting
    -0.81
    doors
    -0.80
    gart
    -0.80
    nov
    -0.79
    glers
    -0.78
    roman
    -0.78
    fitted
    -0.78
    marked
    -0.77
    POSITIVE LOGITS
     Chandler
    0.77
     Grill
    0.74
     Parsons
    0.73
     Crawford
    0.73
     Davis
    0.72
     Kramer
    0.72
     Foods
    0.72
     Reeves
    0.69
     Phillips
    0.69
     Reyes
    0.69
    Act Density 0.036%

    No Known Activations