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

    Neuronpedia

    INDEX
    Explanations

    references to royal titles and members of royal families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptor
    -0.16
     chave
    -0.15
    çĪ½
    -0.15
    åįļ士
    -0.14
    áÄį
    -0.14
    azor
    -0.13
    adius
    -0.13
    uld
    -0.13
    wner
    -0.13
    /fixtures
    -0.13
    POSITIVE LOGITS
     Consort
    0.22
     Prince
    0.22
     Princess
    0.21
     princ
    0.21
    Prince
    0.19
     consort
    0.19
     Inf
    0.18
    morgan
    0.18
     princes
    0.17
     Consent
    0.17
    Act Density 0.029%

    No Known Activations