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

    Neuronpedia

    INDEX
    Explanations

    references to royalty or kingship

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Uhm
    -0.97
     $_"
    -0.94
     "..\..\
    -0.91
     للمعارف
    -0.91
     Bambi
    -0.91
    Lom
    -0.90
     Radu
    -0.88
     Pelt
    -0.88
    __)
    -0.88
     Schrö
    -0.87
    POSITIVE LOGITS
    ing
    1.25
     King
    1.04
     KING
    1.02
    King
    0.99
    ING
    0.96
    i
    0.92
     Kings
    0.91
    o
    0.81
    king
    0.79
     king
    0.76
    Act Density 0.010%

    No Known Activations