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

    Neuronpedia

    INDEX
    Explanations

    mentions of metropolitan areas

    oai_token-act-pair · gpt-3.5-turbo

    references to metropolitan areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    witch
    -0.76
     Secrets
    -0.69
    manship
    -0.65
    Hunt
    -0.64
     Davies
    -0.63
    Chain
    -0.62
    ITION
    -0.62
    Force
    -0.62
    Hol
    -0.61
    ith
    -0.61
    POSITIVE LOGITS
     metro
    3.80
     metropolitan
    2.39
     Metro
    1.74
     suburbs
    1.62
    Metro
    1.48
     subway
    1.41
     suburban
    1.31
     Metropolitan
    1.30
     suburb
    1.22
    ropolitan
    1.17
    Act Density 0.011%

    No Known Activations