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

    Neuronpedia

    INDEX
    Explanations

    the word "faire" or variations of it in the context of fairness, justice, or equality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fairness and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.86
    kson
    -0.76
    ITED
    -0.73
     Grill
    -0.70
     Barcl
    -0.66
     Records
    -0.65
     Presence
    -0.65
     Slug
    -0.64
    ebus
    -0.64
     Emer
    -0.64
    POSITIVE LOGITS
    rative
    1.26
    rant
    1.16
    rance
    0.99
    rals
    0.96
    stration
    0.96
    ration
    0.95
    rants
    0.93
    anced
    0.91
    ral
    0.91
    rated
    0.88
    Act Density 0.027%

    No Known Activations