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

    Neuronpedia

    INDEX
    Explanations

    references to royalty and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compri
    -0.72
     itſelf
    -0.68
     Lovato
    -0.68
    antaine
    -0.66
     Dars
    -0.66
     evan
    -0.66
    pertory
    -0.65
    eradish
    -0.65
     Prakash
    -0.64
     Travis
    -0.64
    POSITIVE LOGITS
     Kings
    1.58
     kings
    1.49
     KING
    1.48
     King
    1.47
     king
    1.33
    Kings
    1.33
     KINGS
    1.26
    King
    1.24
    👑
    1.17
     Queen
    1.11
    Act Density 0.106%

    No Known Activations