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

    Neuronpedia

    INDEX
    Explanations

    email-related content such as addresses and newsletters giveaways

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    liga
    -0.80
    TRY
    -0.75
    ICLE
    -0.69
    steen
    -0.68
    OWER
    -0.66
     Vanderbilt
    -0.65
    stru
    -0.65
    imposed
    -0.64
     Bourbon
    -0.63
    Jere
    -0.63
    POSITIVE LOGITS
     inbox
    1.25
     address
    1.22
     correspondence
    1.11
     addresses
    1.10
    address
    0.99
     Address
    0.99
    email
    0.97
     newsletters
    0.92
     messages
    0.88
     invitation
    0.87
    Act Density 0.539%

    No Known Activations