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

    Neuronpedia

    INDEX
    Explanations

    phrases related to racial identity and communities

    oai_token-act-pair · gpt-3.5-turbo

    themes related to societal structures and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.85
    laughs
    -0.79
    bench
    -0.76
    pps
    -0.75
     Ples
    -0.74
    setup
    -0.73
     Cases
    -0.72
    arthed
    -0.71
    batch
    -0.70
    ograp
    -0.69
    POSITIVE LOGITS
     colonialism
    1.13
     masculinity
    1.13
     oppression
    1.11
     purity
    1.10
     sexuality
    1.06
     imperialism
    1.05
     patriarchy
    1.04
     superiority
    1.03
     ideals
    1.03
     nationalism
    1.03
    Act Density 0.839%

    No Known Activations