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

    Neuronpedia

    INDEX
    Explanations

    structural elements like headings or titles in documents

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withd
    -0.78
     tides
    -0.72
     outlet
    -0.70
     casting
    -0.69
     dared
    -0.67
    guards
    -0.66
     overlooked
    -0.66
     neighb
    -0.65
     padd
    -0.65
     casts
    -0.64
    POSITIVE LOGITS
     [+
    1.16
     Introduction
    1.00
     Conclusion
    0.92
    jpg
    0.91
     Purpose
    0.82
     Thou
    0.79
     Learns
    0.79
    Reviewer
    0.78
    png
    0.77
    0
    0.76
    Act Density 0.096%

    No Known Activations