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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of individuals in context, such as former players, officials, or political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    otle
    -0.83
    ramid
    -0.78
    aris
    -0.78
    anguage
    -0.76
    ghai
    -0.76
    uden
    -0.75
    opping
    -0.73
    iquette
    -0.70
    oked
    -0.70
    antics
    -0.69
    POSITIVE LOGITS
     Yugoslav
    1.06
     Yugoslavia
    1.04
     president
    1.01
     Soviet
    0.99
     President
    0.94
     colleague
    0.94
     comrade
    0.91
     employee
    0.91
     presidents
    0.91
     employer
    0.90
    Act Density 1.441%

    No Known Activations