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

    Neuronpedia

    INDEX
    Explanations

    references to advertising and its various forms and impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Advertisement" or "advertising"

    np_acts-logits-general · gemini-2.0-flash

    advertising and commercial content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.41
    Gut
    -0.39
    Core
    -0.39
    Point
    -0.39
            
    -0.39
     Eul
    -0.38
    <u>
    -0.38
    thyst
    -0.38
     Gut
    -0.38
          
    -0.38
    POSITIVE LOGITS
     advertisement
    1.16
     Advertisement
    1.13
     advertisements
    1.07
     Advertising
    1.06
     advertising
    1.06
     Advertisements
    1.05
    adverti
    1.02
     adverts
    0.99
     Ads
    0.98
     ads
    0.97
    Act Density 0.093%

    No Known Activations