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

    Neuronpedia

    INDEX
    Explanations

    geographical locations or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographic concepts and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -1.12
    alin
    -1.03
    rin
    -0.88
    enment
    -0.84
    ion
    -0.82
    ework
    -0.80
    nos
    -0.79
    rahim
    -0.79
    ublic
    -0.78
    rentice
    -0.77
    POSITIVE LOGITS
     coordinates
    1.02
     footprint
    0.97
     proximity
    0.89
     geography
    0.88
     boundaries
    0.86
     location
    0.86
     locations
    0.85
     distances
    0.83
     instability
    0.81
     geographic
    0.80
    Act Density 0.017%

    No Known Activations