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

    Neuronpedia

    INDEX
    Explanations

    software tutorials and instructions

    oai_token-act-pair · gpt-3.5-turbo

    instructional and tutorial-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soType
    -0.89
    */(
    -0.75
     Crosby
    -0.74
     texted
    -0.72
    76561
    -0.70
     tweeted
    -0.68
    ween
    -0.67
     tweeting
    -0.67
     vetoed
    -0.66
    Lago
    -0.63
    POSITIVE LOGITS
    Introduction
    1.44
     Introduction
    1.33
     overview
    1.32
     tutorial
    1.20
     Topics
    1.19
    Chapter
    1.18
     introduction
    1.17
     introductory
    1.15
    chapter
    1.15
     topics
    1.14
    Act Density 0.601%

    No Known Activations