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

    Neuronpedia

    INDEX
    Explanations

    mentions of politicians

    oai_token-act-pair · gpt-3.5-turbo

    references to politicians

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kit
    -0.67
    bender
    -0.65
    imeter
    -0.63
    mage
    -0.62
    ettle
    -0.61
    inth
    -0.61
    iHUD
    -0.61
    Depth
    -0.61
    ooth
    -0.60
    tesy
    -0.60
    POSITIVE LOGITS
     politicians
    3.33
     politician
    2.30
     legislators
    2.22
     lawmakers
    2.15
     policymakers
    2.05
     MPs
    1.90
     mayors
    1.89
     councillors
    1.85
     governments
    1.85
     bureaucrats
    1.76
    Act Density 0.022%

    No Known Activations