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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government policies and financial matters

    oai_token-act-pair · gpt-3.5-turbo

    references to government spending and taxation issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igmatic
    -0.86
    canon
    -0.71
     Proto
    -0.69
    inarily
    -0.68
     consistency
    -0.65
    erning
    -0.65
    ItemImage
    -0.65
     calm
    -0.64
    pring
    -0.64
    rief
    -0.63
    POSITIVE LOGITS
     trillions
    1.56
     bloated
    1.30
     subsidies
    1.21
     wasteful
    1.21
     privat
    1.20
     giveaways
    1.19
     billions
    1.19
     trillion
    1.17
     taxpayer
    1.17
     wars
    1.16
    Act Density 0.650%

    No Known Activations