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

    Neuronpedia

    INDEX
    Explanations

    references to different countries and regions

    oai_token-act-pair · gpt-3.5-turbo

    references to government or political entities, particularly those containing "Republic of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anos
    -0.77
    setting
    -0.75
    afety
    -0.74
     nets
    -0.73
     grave
    -0.71
    angelo
    -0.69
    abus
    -0.68
    bath
    -0.67
    netflix
    -0.66
    icidal
    -0.65
    POSITIVE LOGITS
     Congo
    0.89
    foundland
    0.87
     Latvia
    0.80
     Yugoslavia
    0.79
     Emirates
    0.72
     Lie
    0.71
    Ò
    0.71
     Somalia
    0.70
     Korea
    0.70
     Macedonia
    0.70
    Act Density 0.048%

    No Known Activations