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

    Neuronpedia

    INDEX
    Explanations

    words related to political ideologies and societal norms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to societal issues and power dynamics involving various groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.83
    hid
    -0.82
    liga
    -0.81
    isode
    -0.81
    linger
    -0.79
    trak
    -0.77
    ikarp
    -0.77
    phe
    -0.76
    epad
    -0.76
    slot
    -0.76
    POSITIVE LOGITS
     supremacy
    0.96
     institutions
    0.91
     casualties
    0.91
     hegemony
    0.89
     civilization
    0.88
     populations
    0.88
     sovereignty
    0.88
     civilizations
    0.86
     conceptions
    0.85
     opponents
    0.85
    Act Density 0.432%

    No Known Activations