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

    Neuronpedia

    INDEX
    Explanations

    references to government and political structures

    oai_token-act-pair · gpt-3.5-turbo

    references to ownership and personal connections within discussions of governance and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     havoc
    -0.76
     pseudonym
    -0.68
    utra
    -0.66
    Wikipedia
    -0.64
     alias
    -0.64
    lance
    -0.62
     honor
    -0.61
    lycer
    -0.59
    icut
    -0.58
     surn
    -0.57
    POSITIVE LOGITS
     stakeholders
    1.39
     creditors
    1.27
     constituents
    1.19
     allies
    1.18
     adversaries
    1.18
     detractors
    1.16
     policymakers
    1.14
     lenders
    1.13
     shareholders
    1.13
     peers
    1.12
    Act Density 0.526%

    No Known Activations