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

    Neuronpedia

    INDEX
    Explanations

    mentions of government policies, regulations, and international relations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to regulatory and governmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     freaking
    -0.80
     cops
    -0.79
     buddies
    -0.76
     phony
    -0.76
     colorful
    -0.75
    JUST
    -0.75
     dudes
    -0.75
     afterward
    -0.73
     Nope
    -0.73
     .)
    -0.73
    POSITIVE LOGITS
     organis
    1.26
     recognised
    1.25
     Whilst
    1.25
     emphas
    1.21
     envis
    1.21
     recognise
    1.18
     util
    1.16
     ageing
    1.12
     adversely
    1.12
     favourable
    1.10
    Act Density 0.962%

    No Known Activations