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

    Neuronpedia

    INDEX
    Explanations

    the name "John"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "John."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scale
    -0.75
     2018
    -0.72
     daily
    -0.71
     run
    -0.68
     benchmark
    -0.67
    ures
    -0.67
     endurance
    -0.67
     cooking
    -0.66
     planned
    -0.66
     ultra
    -0.66
    POSITIVE LOGITS
    John
    3.04
    JOHN
    1.93
    john
    1.90
    Matthew
    1.58
    Jane
    1.54
    James
    1.53
    Johnny
    1.52
    Joe
    1.48
    Jeff
    1.47
     john
    1.46
    Act Density 0.018%

    No Known Activations