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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific city names, particularly focusing on capital cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various capitals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    potion
    -0.80
    AUT
    -0.76
    sbm
    -0.76
    akers
    -0.73
    wd
    -0.70
    eker
    -0.70
    ĪĴ
    -0.69
    Choice
    -0.68
    hner
    -0.67
    MpServer
    -0.67
    POSITIVE LOGITS
     metropolitan
    0.91
     city
    0.86
     suburb
    0.81
     cities
    0.80
    itals
    0.76
    uania
    0.76
     metro
    0.74
     Manila
    0.71
    ashtra
    0.70
    omach
    0.70
    Act Density 0.017%

    No Known Activations