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

    Neuronpedia

    INDEX
    Explanations

    subscriptions or calls to action prompting someone to receive updates or information

    oai_token-act-pair · gpt-3.5-turbo

    encouragement to subscribe to newsletters or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scape
    -0.71
    esan
    -0.68
    ilde
    -0.66
    mong
    -0.64
    put
    -0.63
     misunderstanding
    -0.62
     rounding
    -0.61
     curv
    -0.61
    ball
    -0.60
    ondo
    -0.59
    POSITIVE LOGITS
    Subscribe
    1.07
     Subscribe
    1.05
     Emails
    0.88
    Spons
    0.87
    Alert
    0.85
    ï¸
    0.80
    éĹĺ
    0.80
    ables
    0.80
     subscribers
    0.75
    isodes
    0.75
    Act Density 0.008%

    No Known Activations