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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific actions or activities related to different groups of people

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to the needs and historical experiences of various ethnic and racial groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     synergy
    -0.76
     bidder
    -0.68
     burner
    -0.68
     manag
    -0.66
     overhead
    -0.66
     competitor
    -0.66
     optimization
    -0.65
     drawback
    -0.63
     ellipt
    -0.63
    performance
    -0.62
    POSITIVE LOGITS
     Liberties
    0.81
    joice
    0.79
     Boko
    0.78
     revol
    0.77
     persecuted
    0.77
     Franc
    0.75
     Presbyter
    0.74
     murdered
    0.73
    haw
    0.72
     enslaved
    0.72
    Act Density 0.555%

    No Known Activations