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

    Neuronpedia

    INDEX
    Explanations

    words related to unfairness or injustice

    oai_token-act-pair · gpt-3.5-turbo

    expressions of unfairness or injustice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odiac
    -0.72
    morph
    -0.68
     Chili
    -0.64
     pant
    -0.63
     reservoir
    -0.61
    QL
    -0.60
     recovered
    -0.60
     Diet
    -0.60
     Active
    -0.60
    ires
    -0.59
    POSITIVE LOGITS
     unfair
    3.57
     unfairly
    2.09
     unjust
    2.02
     injustice
    1.78
     unreasonable
    1.66
     inequ
    1.65
     fairness
    1.52
     dishonest
    1.50
     undue
    1.49
     disproportionate
    1.48
    Act Density 0.027%

    No Known Activations