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

    Neuronpedia

    INDEX
    Explanations

    locations and cities

    oai_token-act-pair · gpt-3.5-turbo

    references to major cities and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idae
    -0.90
    xual
    -0.82
     facult
    -0.79
    Versions
    -0.78
     bip
    -0.78
    shield
    -0.76
    omorph
    -0.75
    attribute
    -0.75
     antibodies
    -0.71
    potion
    -0.71
    POSITIVE LOGITS
     Los
    1.39
     Chicago
    1.35
     Shanghai
    1.35
     Seattle
    1.31
     Minneapolis
    1.30
     Paris
    1.29
     Osaka
    1.29
     Cairo
    1.29
     London
    1.28
     Indianapolis
    1.27
    Act Density 0.263%

    No Known Activations