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

    Neuronpedia

    INDEX
    Explanations

    references to village names

    oai_token-act-pair · gpt-3.5-turbo

    references to villages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.77
    reme
    -0.76
    umbn
    -0.76
    zona
    -0.74
    andem
    -0.74
    roxy
    -0.70
    henko
    -0.69
    trump
    -0.68
    male
    -0.67
    ysical
    -0.67
    POSITIVE LOGITS
     villages
    0.99
     village
    0.93
     Village
    0.80
     outpost
    0.78
     villagers
    0.74
     Massacre
    0.74
     âĵĺ
    0.74
     Settlement
    0.73
     dwell
    0.72
     Shal
    0.71
    Act Density 0.016%

    No Known Activations