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

    Neuronpedia

    INDEX
    Explanations

    titles of royalty, specifically the word "Emperor"

    oai_token-act-pair · gpt-4-turbo

    references to historical figures, specifically emperors

    oai_token-act-pair · gpt-3.5-turbo

    references to emperors and imperial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ter
    -0.79
    chel
    -0.77
    trak
    -0.73
    asket
    -0.73
    esville
    -0.72
    ties
    -0.71
    tera
    -0.71
    nel
    -0.70
    crew
    -0.69
    dos
    -0.67
    POSITIVE LOGITS
    peror
    1.07
     Nero
    1.04
    perors
    1.02
     emperor
    0.92
     Emperor
    0.92
     pengu
    0.90
    esses
    0.83
     Napoleon
    0.81
     Claud
    0.79
     Augustus
    0.75
    Act Density 0.008%

    No Known Activations