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

    Neuronpedia

    INDEX
    Explanations

    email timestamps and related email content

    oai_token-act-pair · gpt-3.5-turbo

    structured email metadata information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     temples
    -0.89
    aepernick
    -0.76
     Furious
    -0.71
     meter
    -0.67
     rhy
    -0.65
     premie
    -0.64
     Tsukuyomi
    -0.63
     joints
    -0.63
     infographic
    -0.63
     Kard
    -0.62
    POSITIVE LOGITS
    olicited
    1.10
     Abedin
    0.94
    afort
    0.91
     Received
    0.80
    mail
    0.80
    Guest
    0.79
     forwarded
    0.78
    Mail
    0.77
    Message
    0.77
     NOTICE
    0.76
    Act Density 0.124%

    No Known Activations