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

    Neuronpedia

    INDEX
    Explanations

    references to royalty and monarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Réponses
    -0.67
     compri
    -0.66
    hiker
    -0.58
     spol
    -0.56
     Travis
    -0.54
     apport
    -0.53
     detail
    -0.53
    provoking
    -0.52
    doit
    -0.52
    eradish
    -0.52
    POSITIVE LOGITS
     Kings
    1.18
     kings
    1.17
     Royalty
    1.16
     Koenig
    1.16
    crowned
    1.13
     royal
    1.13
     monarch
    1.11
     ROYAL
    1.07
    👑
    1.06
    Kings
    1.05
    Act Density 0.186%

    No Known Activations