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

    Neuronpedia

    INDEX
    Explanations

    references to past connections or relationships with someone or something

    oai_token-act-pair · gpt-3.5-turbo

    references to previous roles or statuses of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.98
    otle
    -0.91
    anguage
    -0.83
    andise
    -0.81
    onso
    -0.76
    antics
    -0.75
    allery
    -0.74
    ourced
    -0.73
    ghai
    -0.73
    acht
    -0.72
    POSITIVE LOGITS
     Yugoslavia
    0.96
     Yugoslav
    0.95
     Soviet
    0.82
     captives
    0.78
     comrade
    0.76
     dictator
    0.76
     Lum
    0.75
     President
    0.75
     wartime
    0.75
     comrades
    0.75
    Act Density 0.029%

    No Known Activations