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

    Neuronpedia

    INDEX
    Explanations

    phrases related to addressing social issues and injustices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Inventory
    -0.72
     Folder
    -0.65
     Remy
    -0.64
     Explosion
    -0.62
     Manufacturer
    -0.62
     pandemonium
    -0.61
     Farn
    -0.60
     Delivery
    -0.60
     Pair
    -0.59
     Peoples
    -0.58
    POSITIVE LOGITS
     genuinely
    1.02
     offended
    0.91
     legitimately
    0.91
     willing
    0.89
     otherwise
    0.89
     harmed
    0.89
     victimized
    0.86
     actively
    0.86
     interested
    0.85
     impacted
    0.85
    Act Density 0.188%

    No Known Activations