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

    Neuronpedia

    INDEX
    Explanations

    sections or headings within academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tø
    -0.53
    Klas
    -0.53
     secas
    -0.52
     parish
    -0.52
     Monfieur
    -0.52
    ρχ
    -0.52
     assurent
    -0.50
    Dữ
    -0.50
     Constituency
    -0.49
     fraî
    -0.49
    POSITIVE LOGITS
    Introduction
    1.18
    Conclusions
    1.13
     Conclusions
    1.12
    Foreword
    1.11
    FOREWORD
    1.11
    INTRODUCTION
    1.09
    Conclusion
    1.07
     Conclusion
    1.07
    Preface
    1.05
    CONCLUSION
    1.04
    Act Density 0.185%

    No Known Activations