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

    Neuronpedia

    INDEX
    Explanations

    references to royalty and nobility, particularly kings and queens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toMatchSnapshot
    -0.60
    laşı
    -0.59
     XCTest
    -0.58
    úrese
    -0.57
    verwijspagina
    -0.56
    tichetta
    -0.54
    ьа
    -0.52
    ühlen
    -0.52
    ագրություններ
    -0.52
    })*/
    -0.51
    POSITIVE LOGITS
     king
    4.26
     King
    3.99
     KING
    3.70
    King
    3.67
     kings
    3.34
     Kings
    3.09
    king
    2.94
    KING
    2.78
    kings
    2.67
    Kings
    2.59
    Act Density 0.053%

    No Known Activations