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

    Neuronpedia

    INDEX
    Explanations

    mention of geographical locations, particularly villages

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific villages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    henko
    -0.83
    pter
    -0.83
    inventoryQuantity
    -0.82
    ï¸
    -0.82
    nyder
    -0.74
    odynam
    -0.71
    afort
    -0.70
    xon
    -0.70
    ulative
    -0.69
    roxy
    -0.69
    POSITIVE LOGITS
     villages
    0.93
    folk
    0.90
     village
    0.88
     Adin
    0.88
     elders
    0.83
     outpost
    0.81
     cemetery
    0.76
    hood
    0.75
     Shal
    0.74
     villagers
    0.74
    Act Density 0.047%

    No Known Activations