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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific administrative region or district

    oai_token-act-pair · gpt-3.5-turbo

    references to specific districts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issan
    -0.88
    vous
    -0.76
    IGHTS
    -0.74
    etheus
    -0.74
    thia
    -0.71
    fuel
    -0.70
    glers
    -0.70
    obs
    -0.69
    xon
    -0.69
    pload
    -0.68
    POSITIVE LOGITS
     district
    0.90
     districts
    0.85
    rict
    0.84
     ancest
    0.79
     boundaries
    0.74
    mates
    0.72
    rats
    0.72
    ricting
    0.70
     allot
    0.68
     District
    0.67
    Act Density 0.013%

    No Known Activations