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

    Neuronpedia

    INDEX
    Explanations

    mentions of legislation and policy changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential increases or economic impacts of legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Temper
    -0.78
     legends
    -0.74
     Colors
    -0.71
     Fiesta
    -0.69
     Tee
    -0.69
     reperto
    -0.69
     Semin
    -0.68
     Seasons
    -0.68
     Guru
    -0.68
     Cups
    -0.67
    POSITIVE LOGITS
    stros
    0.89
     unconstitutional
    0.89
    elfare
    0.86
     aimed
    0.81
    ractical
    0.81
    benefit
    0.79
    effect
    0.79
     repealed
    0.77
     fail
    0.77
     undo
    0.76
    Act Density 0.502%

    No Known Activations