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

    Neuronpedia

    INDEX
    Explanations

    references to royalty and inheritance

    oai_token-act-pair · gpt-3.5-turbo

    references to thrones and related royal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Greenberg
    -0.75
     Morse
    -0.72
    aturdays
    -0.68
    velength
    -0.67
    href
    -0.67
     Rossi
    -0.66
    alez
    -0.65
    omal
    -0.65
    é¾
    -0.64
    ãģ¦
    -0.64
    POSITIVE LOGITS
     throne
    1.20
    pole
    0.95
     coffers
    0.84
    holder
    0.83
     Throne
    0.83
    holders
    0.78
     holder
    0.78
     flush
    0.76
    archy
    0.76
     jewels
    0.74
    Act Density 0.011%

    No Known Activations