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

    Neuronpedia

    INDEX
    Explanations

    email-related terms and error messages

    oai_token-act-pair · gpt-3.5-turbo

    references to invalid email addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icles
    -0.86
    laus
    -0.85
    icle
    -0.79
    itive
    -0.77
    mental
    -0.74
    igs
    -0.74
    roo
    -0.73
    steen
    -0.72
    ItemTracker
    -0.71
    abouts
    -0.70
    POSITIVE LOGITS
     sender
    0.93
     inbox
    0.93
     address
    0.82
     notification
    0.80
     Email
    0.79
     email
    0.79
     invitation
    0.75
    email
    0.73
     sent
    0.73
     Verd
    0.71
    Act Density 0.018%

    No Known Activations