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

    Neuronpedia

    INDEX
    Explanations

    references to government budget-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to budgets and financial analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "]=>
    -0.87
    pieces
    -0.79
    auga
    -0.74
    hips
    -0.71
    soc
    -0.71
    ivas
    -0.70
    wo
    -0.69
    pires
    -0.69
    ITH
    -0.67
    Naz
    -0.67
    POSITIVE LOGITS
     Responsibility
    0.87
    vernment
    0.87
     reconciliation
    0.85
    ary
    0.76
     Blueprint
    0.76
    udget
    0.75
     Accountability
    0.74
     Analyst
    0.73
     Estimates
    0.73
    edia
    0.73
    Act Density 0.015%

    No Known Activations