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

    Neuronpedia

    INDEX
    Explanations

    sections that signify the beginning or introduction of a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.68
     للمعارف
    -0.66
    osoba
    -0.63
     "..\..\..\
    -0.62
    المناصب
    -0.62
     חיצוניים
    -0.62
     تضيفلها
    -0.61
     "..\..\
    -0.58
    LAHOMA
    -0.58
    kym
    -0.57
    POSITIVE LOGITS
    Introduction
    1.10
     Introduction
    1.00
     introduction
    0.88
    INTRODUCTION
    0.86
    introduction
    0.85
     overview
    0.85
     INTRODUCTION
    0.83
     Intro
    0.83
    Intro
    0.80
    INTRO
    0.78
    Act Density 0.083%

    No Known Activations