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

    Neuronpedia

    INDEX
    Explanations

    technical terms and keywords related to documentation and information sharing, such as "policy background," "document overview," and "installation."

    oai_token-act-pair · gpt-3.5-turbo

    fragments of text or sections related to various topics or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attled
    -0.71
    ously
    -0.65
    feld
    -0.65
    ivably
    -0.63
    equal
    -0.60
     dared
    -0.60
    Brit
    -0.59
     texted
    -0.59
     Farrell
    -0.59
    boats
    -0.59
    POSITIVE LOGITS
     Definitions
    1.18
    Overview
    1.15
     Overview
    1.09
     Introduction
    0.98
     Basics
    0.96
    Introduction
    0.93
     Summary
    0.92
     Background
    0.92
     nutshell
    0.91
     basics
    0.89
    Act Density 0.909%

    No Known Activations