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

    Neuronpedia

    INDEX
    Explanations

    references to "King."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lovato
    -0.85
    thalten
    -0.72
    CloseOperation
    -0.72
     themſelves
    -0.71
    ])).
    -0.68
    ."),
    -0.68
    __)
    -0.66
    ."],
    -0.66
     Semin
    -0.66
    圳
    -0.66
    POSITIVE LOGITS
     King
    2.69
    King
    2.45
     KING
    2.44
     king
    2.33
     Kings
    2.23
     kings
    2.01
    Kings
    1.83
    KING
    1.81
    king
    1.74
     KINGS
    1.71
    Act Density 0.035%

    No Known Activations