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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proposed actions, laws, or regulations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyal
    -0.91
    vation
    -0.74
    strap
    -0.73
    tesy
    -0.72
    respect
    -0.72
    ilight
    -0.71
    mone
    -0.70
    seed
    -0.70
    vin
    -0.70
    wood
    -0.70
    POSITIVE LOGITS
     proposals
    1.04
     amendments
    1.03
     legislation
    0.90
     proposal
    0.85
     proposing
    0.83
     amendment
    0.82
     revisions
    0.81
     changes
    0.80
     amend
    0.80
     reforms
    0.79
    Act Density 0.036%

    No Known Activations