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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific village names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "village" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    henko
    -0.81
    ept
    -0.76
    sis
    -0.76
    ï¸
    -0.76
    zona
    -0.75
    umbn
    -0.75
    rencies
    -0.72
    roxy
    -0.71
    pter
    -0.70
    andem
    -0.70
    POSITIVE LOGITS
     villages
    0.98
     village
    0.91
    folk
    0.84
     elders
    0.78
     Village
    0.77
     outpost
    0.77
     kitchens
    0.76
     gardens
    0.75
     Adin
    0.75
    hood
    0.74
    Act Density 0.026%

    No Known Activations