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

    Neuronpedia

    INDEX
    Explanations

    references to North America or American entities

    oai_token-act-pair · gpt-3.5-turbo

    references to North America

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regor
    -0.81
    raph
    -0.79
    roo
    -0.79
    gerald
    -0.75
    cellent
    -0.74
    tle
    -0.72
    retty
    -0.72
    fields
    -0.71
    patrick
    -0.71
    flies
    -0.71
    POSITIVE LOGITS
     Federation
    0.83
     Airways
    0.75
     Networks
    0.69
     Union
    0.68
     Society
    0.68
     federation
    0.68
     Aerospace
    0.67
     Territories
    0.67
     feder
    0.67
     separatist
    0.65
    Act Density 0.031%

    No Known Activations