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

    Neuronpedia

    INDEX
    Explanations

    words related to injustice or unfairness

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with unfairness or injustice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gdala
    -0.88
    ince
    -0.81
    udder
    -0.77
    audi
    -0.76
    acid
    -0.76
    apse
    -0.74
    incinn
    -0.72
    asio
    -0.71
    hent
    -0.71
    aeda
    -0.71
    POSITIVE LOGITS
     unfair
    0.90
    nesses
    0.88
     burdens
    0.84
     dismissal
    0.82
     prejudice
    0.81
     burden
    0.78
     Advantage
    0.75
     undermin
    0.72
     unfairly
    0.72
     disadvantages
    0.72
    Act Density 0.043%

    No Known Activations