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

    Neuronpedia

    INDEX
    Explanations

    references to trade agreements or deals

    oai_token-act-pair · gpt-3.5-turbo

    references to political or trade agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atural
    -0.81
    ixel
    -0.78
    erd
    -0.76
    iple
    -0.75
    igne
    -0.75
    osc
    -0.72
    skill
    -0.71
    CTV
    -0.71
    asus
    -0.71
    rh
    -0.70
    POSITIVE LOGITS
     treaties
    0.97
     treaty
    0.93
     breaker
    0.84
     NAFTA
    0.83
    breaker
    0.77
     negotiated
    0.77
     legalizing
    0.76
    breakers
    0.76
     ratified
    0.75
     Implementation
    0.74
    Act Density 0.042%

    No Known Activations