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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, likely with a focus on their achievements or titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.69
    artney
    -0.66
    ople
    -0.65
    ccoli
    -0.62
    bnb
    -0.62
    accompan
    -0.61
    ellar
    -0.61
     arteries
    -0.58
     ponies
    -0.58
     distingu
    -0.58
    POSITIVE LOGITS
    mann
    0.95
    wald
    0.84
    ipel
    0.78
    heim
    0.77
    stadt
    0.77
     Pradesh
    0.75
    GMT
    0.72
    kamp
    0.72
    abeth
    0.71
    uddin
    0.69
    Act Density 0.185%

    No Known Activations