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

    Neuronpedia

    INDEX
    Explanations

    geographic locations, specifically cities and states

    oai_token-act-pair · gpt-4-turbo

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic locations and associated places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TRUMP
    -0.69
    BALL
    -0.62
    wcsstore
    -0.62
    BOOK
    -0.59
     recip
    -0.58
    htaking
    -0.58
    bably
    -0.55
    ueller
    -0.54
    merce
    -0.54
     positives
    -0.53
    POSITIVE LOGITS
     City
    0.69
     Falls
    0.69
     Bay
    0.67
     Harbor
    0.67
     Hills
    0.67
     township
    0.66
     Angeles
    0.66
     countryside
    0.66
     Township
    0.64
     Province
    0.64
    Act Density 0.603%

    No Known Activations