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

    Neuronpedia

    INDEX
    Explanations

    references to monarchs, particularly various kings and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.96
     itſelf
    -0.88
     McCabe
    -0.88
     themſelves
    -0.86
    epam
    -0.85
     Lovato
    -0.84
    ."],
    -0.81
    __)
    -0.81
     ſeveral
    -0.80
    setopt
    -0.79
    POSITIVE LOGITS
     King
    1.64
     KING
    1.60
     Kings
    1.59
    King
    1.44
     kings
    1.41
     king
    1.39
    Kings
    1.28
     KINGS
    1.21
    king
    1.19
    KING
    1.14
    Act Density 0.046%

    No Known Activations