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

    Neuronpedia

    INDEX
    Explanations

    mentions of royal figures or activities

    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
     Extend
    -0.88
    Spread
    -0.83
     Glock
    -0.77
     Caption
    -0.73
    Ñı
    -0.73
    geist
    -0.73
     Apply
    -0.72
    onica
    -0.71
     Loaded
    -0.70
     Canaver
    -0.70
    POSITIVE LOGITS
     royal
    1.04
     decree
    0.97
     princes
    0.95
     palace
    0.92
     prince
    0.90
     roy
    0.87
     immunity
    0.86
     princess
    0.86
     pard
    0.85
     monarchy
    0.85
    Act Density 0.011%

    No Known Activations