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

    Neuronpedia

    INDEX
    Explanations

    references to kingdoms or royalty

    oai_token-act-pair · gpt-3.5-turbo

    references to various kingdoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAST
    -0.80
    esters
    -0.76
    eman
    -0.73
    matter
    -0.72
    inez
    -0.72
    pos
    -0.71
    lder
    -0.70
    eport
    -0.68
    Ñı
    -0.65
    gotten
    -0.64
    POSITIVE LOGITS
    DOM
    1.09
     Hearts
    1.06
     Arabian
    0.92
    wide
    0.91
    doms
    0.85
     Halls
    0.83
     Arabia
    0.82
    loo
    0.79
     kingdom
    0.76
     Aram
    0.76
    Act Density 0.019%

    No Known Activations