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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, likely related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic locations and their relevance or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aph
    -0.64
     heater
    -0.64
     negotiators
    -0.57
     loader
    -0.56
     ransom
    -0.56
     mercy
    -0.56
     acceler
    -0.55
     negotiator
    -0.55
     locom
    -0.55
    enegger
    -0.55
    POSITIVE LOGITS
     Province
    0.98
    opolis
    0.98
    town
    0.95
    region
    0.93
     County
    0.88
    ussia
    0.86
    ulia
    0.86
     City
    0.84
     Highlands
    0.84
    istan
    0.83
    Act Density 0.285%

    No Known Activations