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

    Neuronpedia

    INDEX
    Explanations

    references to royalty or royal-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to royalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LER
    -0.78
     Apply
    -0.76
    Spread
    -0.75
    upon
    -0.73
     Caption
    -0.73
    WAR
    -0.71
    went
    -0.70
     Canaver
    -0.70
    geist
    -0.69
     Shapiro
    -0.69
    POSITIVE LOGITS
     royal
    1.18
     palace
    0.98
     roy
    0.96
     monarchy
    0.96
     pard
    0.91
     decree
    0.89
    pin
    0.87
     princes
    0.85
     princess
    0.83
     intrigue
    0.81
    Act Density 0.005%

    No Known Activations