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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting indicators, such as asterisks and italics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.75
    SourceChecksum
    -0.67
    InputBorder
    -0.61
     surla
    -0.61
     <>",
    -0.60
    ⟬
    -0.59
     snippetHide
    -0.58
    Хьажоргаш
    -0.57
    tonode
    -0.56
    IntoConstraints
    -0.56
    POSITIVE LOGITS
    <em>
    0.99
    <i>
    0.92
    </em>
    0.65
    italic
    0.58
    textit
    0.57
    </i>
    0.55
    Rhestr
    0.48
    mathcal
    0.40
    emph
    0.39
    /*
    0.37
    Act Density 0.800%

    No Known Activations