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

    Neuronpedia

    INDEX
    Explanations

    mentions of political leadership positions in government

    oai_token-act-pair · gpt-3.5-turbo

    references to minority groups in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artney
    -0.88
    akeru
    -0.79
    atche
    -0.78
    aleigh
    -0.76
    hiba
    -0.73
    raltar
    -0.72
    DCS
    -0.71
    DragonMagazine
    -0.70
    icular
    -0.70
    stretched
    -0.70
    POSITIVE LOGITS
     Minority
    1.12
     Majority
    0.97
     Whip
    0.85
     Leader
    0.81
    ority
    0.78
     Voice
    0.74
     outreach
    0.73
     Races
    0.73
     Affairs
    0.71
     Advisory
    0.69
    Act Density 0.008%

    No Known Activations