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

    Neuronpedia

    INDEX
    Explanations

    references to a specific media outlet and subscription-related information

    oai_token-act-pair · gpt-3.5-turbo

    content related to subscriptions and newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oun
    -0.79
    ccording
    -0.69
     pione
    -0.59
     eleph
    -0.58
     helicop
    -0.57
     metic
    -0.57
     tremend
    -0.55
    isSpecial
    -0.54
     practition
    -0.53
     exting
    -0.53
    POSITIVE LOGITS
    Subscribe
    0.58
     subscribing
    0.55
    ceive
    0.52
     newsletter
    0.52
    usercontent
    0.51
     subscriptions
    0.51
    phrine
    0.51
    lect
    0.50
    ]);
    0.50
    ÃĹ
    0.47
    Act Density 0.045%

    No Known Activations