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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically the name "Burke"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly the name "Burke."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesium
    -0.87
    ariat
    -0.79
    icals
    -0.77
    ician
    -0.77
    inence
    -0.76
    obil
    -0.75
    ular
    -0.74
    atural
    -0.74
    oded
    -0.74
    ocre
    -0.72
    POSITIVE LOGITS
     Burke
    0.96
    patrick
    0.87
     Duffy
    0.74
    hound
    0.73
     Wilde
    0.70
     Booth
    0.69
     Parish
    0.69
    Collins
    0.68
     Duff
    0.66
    UGH
    0.66
    Act Density 0.026%

    No Known Activations