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

    Neuronpedia

    INDEX
    Explanations

    words related to cultural or political identities and their characteristics, with a focus on specific groups or ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to various social, religious, and political identities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.84
    lio
    -0.83
    lished
    -0.82
    ainer
    -0.77
    isode
    -0.75
    daq
    -0.73
    ogle
    -0.72
    ortium
    -0.70
    porter
    -0.70
    anse
    -0.69
    POSITIVE LOGITS
     criminality
    1.30
     supremacy
    1.25
    ism
    1.24
    Semitism
    1.24
     superiority
    1.22
     extremism
    1.22
     sovereignty
    1.22
     nationalism
    1.21
     racism
    1.17
     involvement
    1.17
    Act Density 0.321%

    No Known Activations