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

    Neuronpedia

    INDEX
    Explanations

    references to royalty, particularly kings and queens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fromLTRB
    -0.48
    anasia
    -0.46
    hradun
    -0.42
     (;;)
    -0.42
     lopen
    -0.41
     Needham
    -0.40
    arakhand
    -0.40
     jalur
    -0.40
    graffiti
    -0.40
    hysema
    -0.39
    POSITIVE LOGITS
     King
    0.75
    King
    0.71
     king
    0.71
     prince
    0.71
     KING
    0.70
     Queen
    0.70
     Kings
    0.63
     KINGS
    0.62
     queen
    0.62
    Queen
    0.61
    Act Density 0.236%

    No Known Activations