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

    Neuronpedia

    INDEX
    Explanations

    phrases related to prompting or urging action

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to activism or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kered
    -0.79
     discharged
    -0.71
     roast
    -0.68
    endiary
    -0.67
    oxide
    -0.65
     vine
    -0.64
     liner
    -0.64
    sell
    -0.63
     tasting
    -0.63
     aber
    -0.62
    POSITIVE LOGITS
     Funding
    0.88
     Politics
    0.87
     Now
    0.86
     Legislation
    0.83
     GOODMAN
    0.80
     Report
    0.78
     Voter
    0.78
     Measures
    0.77
     Caucus
    0.77
     Issue
    0.76
    Act Density 0.041%

    No Known Activations