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

    Neuronpedia

    INDEX
    Explanations

    email-related actions such as signing up, receiving, and getting notifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscriptions and receiving updates or notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enough
    -0.70
    xia
    -0.65
    iao
    -0.65
    tis
    -0.62
    sie
    -0.60
     Mosque
    -0.59
    too
    -0.59
    gee
    -0.57
     Temper
    -0.57
    enne
    -0.56
    POSITIVE LOGITS
     notifications
    0.98
     alerts
    0.89
     notified
    0.87
     personalized
    0.74
     updates
    0.73
     FREE
    0.72
     notification
    0.72
     announcements
    0.71
     immediate
    0.70
    vertisement
    0.68
    Act Density 0.071%

    No Known Activations