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

    Neuronpedia

    INDEX
    Explanations

    contact information such as phone numbers and websites

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     stacking
    -0.85
     sweets
    -0.68
     stacks
    -0.65
     palate
    -0.64
     stacked
    -0.62
     dominated
    -0.59
     pudding
    -0.58
     gravy
    -0.57
     textbook
    -0.57
     expended
    -0.56
    POSITIVE LOGITS
    Email
    0.89
    Fax
    0.83
    tips
    0.81
    INFO
    0.81
    quit
    0.78
    Phone
    0.76
    76561
    0.76
     toll
    0.74
    email
    0.73
    fax
    0.72
    Act Density 0.087%

    No Known Activations