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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating affiliation disclosure in blog posts

    oai_token-act-pair · gpt-3.5-turbo

    references to affiliate marketing and disclosure of associated commissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itage
    -0.70
     Machina
    -0.68
    Fax
    -0.66
    gow
    -0.65
    hammer
    -0.64
    emer
    -0.64
     Gork
    -0.63
     Esper
    -0.60
     brut
    -0.59
     Stras
    -0.59
    POSITIVE LOGITS
     affiliate
    1.09
     advertising
    0.93
     advertis
    0.90
     compensated
    0.90
    iliate
    0.90
     Disclosure
    0.89
     purchases
    0.88
     coupon
    0.86
     links
    0.85
     coupons
    0.81
    Act Density 0.091%

    No Known Activations