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

    Neuronpedia

    INDEX
    Explanations

    promotional text related to daily newsletters and subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to newsletters and subscription-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yo
    -0.77
    arov
    -0.64
     denomin
    -0.63
    itive
    -0.63
     mole
    -0.63
    wikipedia
    -0.63
    hill
    -0.61
     JPM
    -0.60
     polyg
    -0.59
    paces
    -0.59
    POSITIVE LOGITS
     Thumbnails
    0.82
     Torrent
    0.77
     Newsletter
    0.72
    Interstitial
    0.71
     Subscribe
    0.69
    Scan
    0.67
     Flavoring
    0.67
    iquette
    0.66
     Container
    0.66
    dayName
    0.65
    Act Density 0.067%

    No Known Activations