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

    Neuronpedia

    INDEX
    Explanations

    mentions of geographical locations, with a focus on cities and areas

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, particularly places associated with "Lake"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    binary
    -0.80
    schild
    -0.74
    gets
    -0.70
    hered
    -0.69
     streng
    -0.67
    âĶģ
    -0.66
    mble
    -0.64
    GES
    -0.64
    versions
    -0.64
     mitigating
    -0.63
    POSITIVE LOGITS
     City
    1.01
    apolis
    0.88
     Springs
    0.88
     Arabia
    0.86
     Tribune
    0.84
     Lake
    0.79
     Canyon
    0.76
     Rapids
    0.76
     Falls
    0.74
    City
    0.73
    Act Density 0.018%

    No Known Activations