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

    Neuronpedia

    INDEX
    Explanations

    email subscription prompts

    oai_token-act-pair · gpt-3.5-turbo

    references to email subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arks
    -0.59
     Patriarch
    -0.59
    asio
    -0.59
     Galile
    -0.58
     Targ
    -0.56
    liga
    -0.55
     Inher
    -0.55
     Fren
    -0.52
    iger
    -0.51
     Chaff
    -0.51
    POSITIVE LOGITS
     newsletter
    0.83
     Newsletter
    0.81
     Subscribe
    0.81
     inbox
    0.77
     Birch
    0.74
     address
    0.71
     subscribers
    0.69
     alerts
    0.68
     RSS
    0.68
    Subscribe
    0.68
    Act Density 0.008%

    No Known Activations