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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to royalty

    oai_token-act-pair · gpt-3.5-turbo

    mentions of royalty or princes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.74
    anwhile
    -0.69
    onica
    -0.66
     fram
    -0.66
    KT
    -0.66
    bers
    -0.64
    £ı
    -0.63
    RD
    -0.62
    visors
    -0.61
    ãĤī
    -0.60
    POSITIVE LOGITS
    loo
    0.90
    cipled
    0.86
    doms
    0.84
     Clause
    0.79
     Rupert
    0.77
     Prince
    0.77
    pin
    0.76
     Albert
    0.73
    afort
    0.72
    Prince
    0.71
    Act Density 0.020%

    No Known Activations