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

    Neuronpedia

    INDEX
    Explanations

    questions related to individuals and their qualifications

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or questions about qualifications and job-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lastly
    -0.82
     Lastly
    -0.82
     Overall
    -0.75
    2017
    -0.74
    2016
    -0.71
    Overall
    -0.71
    Examples
    -0.71
    2018
    -0.70
    ividual
    -0.70
    lations
    -0.69
    POSITIVE LOGITS
     instantly
    1.09
     startled
    1.00
     immediately
    0.99
     astonished
    0.99
     promptly
    0.99
     horrified
    0.92
     intrigued
    0.90
     thrilled
    0.88
     duly
    0.87
     aston
    0.86
    Act Density 0.908%

    No Known Activations