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

    Neuronpedia

    INDEX
    Explanations

    terms related to unfairness or injustice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    unfair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abito
    -0.55
    MessageState
    -0.54
     hood
    -0.52
    livejournal
    -0.52
     يتيمه
    -0.52
     vestibule
    -0.52
    initializeApp
    -0.50
     Hause
    -0.49
     frigor
    -0.48
     Tobin
    -0.48
    POSITIVE LOGITS
     unfair
    1.78
     unfairly
    1.25
     unjust
    1.04
     injust
    1.01
     unjustly
    0.79
     injustice
    0.75
     injus
    0.75
     injustices
    0.69
     inequ
    0.65
     unequal
    0.65
    Act Density 0.007%

    No Known Activations