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

    Neuronpedia

    INDEX
    Explanations

    references to social or political debates

    oai_token-act-pair · gpt-3.5-turbo

    themes related to societal attitudes towards diversity and historical perspectives on discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XD
    -0.73
    peed
    -0.69
     TBD
    -0.63
     Flare
    -0.62
    iHUD
    -0.61
     bait
    -0.61
     ASAP
    -0.60
     Chimera
    -0.60
     blockers
    -0.60
    Adds
    -0.60
    POSITIVE LOGITS
     majorities
    1.04
     democracies
    1.04
     liberalism
    0.93
     industrialized
    0.92
    arcer
    0.91
     democratic
    0.90
     neoliberal
    0.90
     Americans
    0.89
     occupations
    0.89
     culturally
    0.88
    Act Density 1.453%

    No Known Activations