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

    Neuronpedia

    INDEX
    Explanations

    references to various monarchs and kings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lovato
    -0.90
    ,$_
    -0.82
     McCabe
    -0.77
    epam
    -0.77
     Radu
    -0.75
    __)
    -0.74
     yep
    -0.73
     Obrador
    -0.72
     Miquel
    -0.72
    pertory
    -0.72
    POSITIVE LOGITS
     King
    1.60
     KING
    1.59
     Kings
    1.57
    King
    1.44
     kings
    1.38
     king
    1.33
    Kings
    1.26
    king
    1.24
     KINGS
    1.18
    KING
    1.18
    Act Density 0.042%

    No Known Activations