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

    Neuronpedia

    INDEX
    Explanations

    references to kingdoms and royal titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Archive
    -0.15
    olla
    -0.15
     carr
    -0.15
    uster
    -0.15
    _argument
    -0.14
    yor
    -0.14
     ballot
    -0.14
    villa
    -0.14
    ACHINE
    -0.14
     quit
    -0.14
    POSITIVE LOGITS
     King
    0.33
    King
    0.33
     king
    0.32
     KING
    0.29
     kings
    0.25
    king
    0.25
     Animalia
    0.25
     royal
    0.24
     Kings
    0.23
     коÑĢол
    0.23
    Act Density 0.065%

    No Known Activations