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

    Neuronpedia

    INDEX
    Explanations

    mentions of royalty, particularly references to princes and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocê
    -0.16
     пÑĢиÑĤ
    -0.16
    ctype
    -0.15
    anmar
    -0.15
     Garland
    -0.15
    ULER
    -0.15
    usan
    -0.15
    vron
    -0.15
    ennon
    -0.14
    ounter
    -0.14
    POSITIVE LOGITS
     Harry
    0.26
    (ss
    0.24
     Charles
    0.24
    /ss
    0.23
     Edward
    0.23
     Philip
    0.23
     Andrew
    0.22
     William
    0.22
     Albert
    0.22
     Consort
    0.21
    Act Density 0.008%

    No Known Activations