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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific locations, specifically focusing on areas near lakes and cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations, specifically places with "Lake" or "City" in their name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.78
    schild
    -0.74
     streng
    -0.71
    gets
    -0.67
    mble
    -0.67
     behavi
    -0.66
    GES
    -0.62
    ilater
    -0.62
    atson
    -0.60
    bye
    -0.60
    POSITIVE LOGITS
     City
    1.10
     Springs
    0.92
     Tribune
    0.89
    apolis
    0.84
    pi
    0.83
     Falls
    0.82
    City
    0.80
     Arabia
    0.77
     Rapids
    0.76
    adelphia
    0.75
    Act Density 0.027%

    No Known Activations