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

    Neuronpedia

    INDEX
    Explanations

    locations or references to 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
    ally
    -0.75
     Archdemon
    -0.73
    igm
    -0.73
    nesota
    -0.72
    unct
    -0.68
    ources
    -0.67
    kick
    -0.65
    guided
    -0.63
    istically
    -0.62
    selection
    -0.61
    POSITIVE LOGITS
     Kong
    1.33
     Hong
    1.12
    Hong
    1.07
    awei
    1.00
     Hua
    0.91
    terness
    0.85
     Guan
    0.81
     Wong
    0.79
     Lumpur
    0.78
     Luo
    0.77
    Act Density 0.007%

    No Known Activations