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

    Neuronpedia

    INDEX
    Explanations

    references to locations involving the term "King."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "King."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TING
    -0.78
    ATIONAL
    -0.76
    eria
    -0.75
    ename
    -0.74
    chell
    -0.71
    ters
    -0.71
    umbai
    -0.70
    Availability
    -0.70
    uated
    -0.70
    ciplinary
    -0.69
    POSITIVE LOGITS
    pin
    1.21
    uin
    1.15
    doms
    1.13
    dom
    1.10
    pins
    1.09
    fish
    1.00
    DOM
    0.94
     Kong
    0.91
    stown
    0.90
    STON
    0.88
    Act Density 0.024%

    No Known Activations