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

    Neuronpedia

    INDEX
    Explanations

    terms related to trade tariffs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tariffs and trade regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itar
    -0.79
    lihood
    -0.76
    VK
    -0.73
     Apostles
    -0.72
    gaard
    -0.68
    uther
    -0.68
     Grey
    -0.67
    esan
    -0.66
    RH
    -0.64
    erva
    -0.63
    POSITIVE LOGITS
     tariffs
    1.12
     tariff
    1.02
     rates
    0.75
    iculty
    0.74
     trade
    0.72
     imports
    0.71
    payers
    0.71
     depreciation
    0.69
    heet
    0.69
    payer
    0.68
    Act Density 0.014%

    No Known Activations