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

    Neuronpedia

    INDEX
    Explanations

    mentions of bipartisan activities or agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bipartisan or bilateral agreements and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ée
    -0.81
    young
    -0.75
    marked
    -0.75
    yth
    -0.73
    geist
    -0.73
    chester
    -0.72
    points
    -0.71
    eon
    -0.70
    wives
    -0.70
    DN
    -0.69
    POSITIVE LOGITS
     agreement
    0.94
     agreements
    0.90
     solutions
    0.90
     nature
    0.89
     efforts
    0.84
     cooperation
    0.84
     majorities
    0.81
     arrangements
    0.80
     bonding
    0.79
     bargaining
    0.78
    Act Density 0.088%

    No Known Activations