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

    Neuronpedia

    INDEX
    Explanations

    terms related to political ideologies and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political ideologies and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shards
    -0.94
     Rings
    -0.82
    ulla
    -0.79
    Sym
    -0.77
     bruises
    -0.76
    ciating
    -0.73
     piles
    -0.73
     Craw
    -0.72
    ãĥ¼ãĥ³
    -0.72
     Sparks
    -0.72
    POSITIVE LOGITS
     fundamentalist
    1.16
     libertarian
    1.12
     liberal
    1.12
     authoritarian
    1.11
     socialist
    1.10
    liberal
    1.09
     populist
    1.09
     totalitarian
    1.08
     egalitarian
    1.06
     progressive
    1.04
    Act Density 0.250%

    No Known Activations