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

    Neuronpedia

    INDEX
    Explanations

    references to trade policies and economic sanctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhl
    -0.16
    tout
    -0.15
    lue
    -0.15
    uby
    -0.14
    deo
    -0.14
    esel
    -0.14
    964
    -0.14
    405
    -0.14
    ÑĢавилÑĮ
    -0.14
    utch
    -0.14
    POSITIVE LOGITS
     tariffs
    0.43
     tariff
    0.40
     Tar
    0.38
    tar
    0.37
     trade
    0.32
     tarif
    0.31
     duties
    0.31
     Trade
    0.31
    Tar
    0.31
     imports
    0.28
    Act Density 0.085%

    No Known Activations