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

    Neuronpedia

    INDEX
    Explanations

    prompts for email subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    calls to action for subscribing to newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.74
    pher
    -0.72
    prototype
    -0.70
    rior
    -0.68
     Stef
    -0.66
    put
    -0.65
    Äĩ
    -0.64
    wikipedia
    -0.64
    esan
    -0.61
    ivas
    -0.60
    POSITIVE LOGITS
     Subscribe
    1.02
    Subscribe
    0.93
    ickets
    0.87
    Interstitial
    0.83
     subscribe
    0.81
     subscriptions
    0.76
     Email
    0.74
     subscribers
    0.74
     Emails
    0.72
     Thumbnails
    0.72
    Act Density 0.009%

    No Known Activations