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

    Neuronpedia

    INDEX
    Explanations

    references to equality-related concepts or terms

    oai_token-act-pair · gpt-3.5-turbo

    references to equality and related social justice concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.72
    stal
    -0.71
    âĸ¬
    -0.66
    ules
    -0.66
    âĸ¬âĸ¬
    -0.66
    KER
    -0.64
    \/\/
    -0.64
    arro
    -0.62
    Extra
    -0.61
    asel
    -0.61
    POSITIVE LOGITS
     Equality
    1.13
     equality
    1.13
    equality
    1.00
    itably
    0.85
     rights
    0.83
    cellence
    0.82
    rights
    0.81
    itarian
    0.81
    marriage
    0.77
    ternity
    0.76
    Act Density 0.023%

    No Known Activations