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

    Neuronpedia

    INDEX
    Explanations

    historical references related to monarchies and significant leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gaul
    -0.17
    ivas
    -0.15
     Constantin
    -0.15
    ruh
    -0.15
    serter
    -0.15
     Throne
    -0.14
     Nile
    -0.14
    deen
    -0.14
     Nisan
    -0.14
    iji
    -0.14
    POSITIVE LOGITS
     King
    0.23
     Princess
    0.21
     Count
    0.20
     Prince
    0.19
     Queen
    0.17
    count
    0.17
    Master
    0.16
     Emperor
    0.16
     Master
    0.16
     Johnston
    0.16
    Act Density 0.215%

    No Known Activations