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

    Neuronpedia

    INDEX
    Explanations

    references to royalty and nobility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     acceptez
    -0.46
    maphore
    -0.46
    Бахар
    -0.45
    Referències
    -0.44
    ungkinkan
    -0.43
    raszamy
    -0.43
     whist
    -0.43
    XmlEnum
    -0.42
     Hid
    -0.41
    ंदीखरीदारी
    -0.41
    POSITIVE LOGITS
     king
    2.53
     kings
    2.44
     royal
    2.31
     queen
    2.11
    royal
    1.94
     royals
    1.85
     monarch
    1.84
    kings
    1.79
     monarchs
    1.77
     royalty
    1.77
    Act Density 0.195%

    No Known Activations