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

    Neuronpedia

    INDEX
    Explanations

    cities or locations, potentially focusing on news and events happening there

    oai_token-act-pair · gpt-3.5-turbo

    city names and associated locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acha
    -0.75
    flat
    -0.72
    rious
    -0.70
    big
    -0.70
    meier
    -0.69
    groups
    -0.69
    uchin
    -0.67
    agy
    -0.67
    lihood
    -0.67
    abet
    -0.66
    POSITIVE LOGITS
     City
    0.85
     Pride
    0.78
     Tourism
    0.76
     Parks
    0.74
     Citiz
    0.73
     municipality
    0.71
     PD
    0.71
     Metropolitan
    0.69
     Rapids
    0.69
     Nights
    0.67
    Act Density 0.372%

    No Known Activations