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

    Neuronpedia

    INDEX
    Explanations

    instances where voting behavior is discussed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "against."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -1.03
    operated
    -0.79
    ãĤ¼ãĤ¦ãĤ¹
    -0.78
    OGR
    -0.75
    mares
    -0.70
    ennes
    -0.69
    ancial
    -0.69
    lycer
    -0.69
    æ©
    -0.69
    overed
    -0.69
    POSITIVE LOGITS
     wasting
    0.79
     prejudice
    0.79
     austerity
    0.74
     discrimination
    0.74
     anybody
    0.73
     independence
    0.73
     worsh
    0.73
     accepting
    0.73
     racism
    0.72
     outsourcing
    0.72
    Act Density 0.035%

    No Known Activations