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

    Neuronpedia

    INDEX
    Explanations

    political buzzwords and terms related to governance and authority

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political power or authority related to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Granger
    -0.83
    hire
    -0.74
     CFL
    -0.70
    chie
    -0.68
     Sins
    -0.66
     Gard
    -0.65
     Pilgrim
    -0.64
     Webster
    -0.64
    activated
    -0.63
    aged
    -0.63
    POSITIVE LOGITS
     ruling
    0.90
    uling
    0.80
     dict
    0.76
    maker
    0.76
    lords
    0.76
    eering
    0.74
     rulings
    0.74
     prevail
    0.73
    makers
    0.72
     rul
    0.71
    Act Density 0.013%

    No Known Activations