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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Hong Kong"

    oai_token-act-pair · gpt-3.5-turbo

    references to Hong Kong

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mileage
    -0.80
     blow
    -0.76
    nesota
    -0.73
     isot
    -0.73
     accuracy
    -0.68
     payoff
    -0.66
     inacc
    -0.65
     exerc
    -0.65
     thumbs
    -0.65
     Accuracy
    -0.63
    POSITIVE LOGITS
     Kong
    1.79
    moon
    1.15
    zhou
    1.12
    awei
    1.12
    wu
    1.10
    jin
    1.08
    qi
    1.05
    wei
    1.03
    pei
    1.02
    jing
    0.97
    Act Density 0.029%

    No Known Activations