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

    Neuronpedia

    INDEX
    Explanations

    information such as titles, subtitles, and section headers in text

    oai_token-act-pair · gpt-3.5-turbo

    references to page titles and headings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skelet
    -0.87
    etheless
    -0.86
    ¥ŀ
    -0.79
     pse
    -0.77
     cryst
    -0.73
     eleph
    -0.72
     afterward
    -0.72
     piled
    -0.72
     estab
    -0.72
     exha
    -0.72
    POSITIVE LOGITS
    Welcome
    1.60
    Introduction
    1.55
    Hello
    1.48
    Description
    1.45
    Overview
    1.43
    Hi
    1.33
    Definition
    1.28
    hello
    1.27
    Synopsis
    1.27
    Quote
    1.27
    Act Density 0.335%

    No Known Activations