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

    Neuronpedia

    INDEX
    Explanations

    topics related to executive orders and policies

    oai_token-act-pair · gpt-3.5-turbo

    references to executive orders and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rown
    -0.91
    dden
    -0.74
    iability
    -0.73
    nia
    -0.69
    Lost
    -0.68
    lehem
    -0.67
    CTV
    -0.67
     Continent
    -0.66
    ENE
    -0.66
    worn
    -0.65
    POSITIVE LOGITS
     entitled
    0.73
     pard
    0.71
     aimed
    0.71
     titled
    0.70
     targeting
    0.70
     legalizing
    0.69
     enacted
    0.69
    book
    0.68
     vetoed
    0.68
     amnesty
    0.68
    Act Density 0.052%

    No Known Activations