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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "contents" and related terms in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.51
    iseksi
    -0.49
    AllowUser
    -0.49
    livejournal
    -0.47
     Circle
    -0.47
     oublié
    -0.47
    PasswordEncoder
    -0.47
     circles
    -0.46
    Circle
    -0.45
    Архівовано
    -0.45
    POSITIVE LOGITS
     Contents
    1.42
     CONTENTS
    1.39
    CONTENTS
    1.23
    Contents
    1.22
     contents
    1.14
    contents
    1.07
     CONTENT
    0.99
     Content
    0.96
    CONTENT
    0.93
    Inhalt
    0.91
    Act Density 0.359%

    No Known Activations