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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "policy" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to policy-related issues and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stain
    -0.76
    Ñĭ
    -0.76
    ingly
    -0.70
    batch
    -0.67
     Cruise
    -0.67
    DAY
    -0.66
    iculture
    -0.66
    apy
    -0.65
    orf
    -0.65
    ibles
    -0.64
    POSITIVE LOGITS
    making
    1.24
     makers
    1.19
    maker
    1.10
    makers
    1.10
     prescriptions
    1.06
    holders
    1.02
     stances
    0.97
    holder
    0.95
     choices
    0.92
     advisor
    0.91
    Act Density 0.051%

    No Known Activations