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

    Neuronpedia

    INDEX
    Explanations

    references to specific topics or categories within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    halb
    -0.86
    <blockquote>
    -0.66
    ecore
    -0.65
    StrictEqual
    -0.64
    <h6>
    -0.63
    cell
    -0.62
    Šaltiniai
    -0.61
     l
    -0.61
    parsedMessage
    -0.61
    𝑙
    -0.60
    POSITIVE LOGITS
     topics
    1.95
     Topic
    1.87
     TOPIC
    1.83
     Topics
    1.78
     topic
    1.77
    Topics
    1.75
    topics
    1.72
    Topic
    1.68
    topic
    1.61
    TOPIC
    1.60
    Act Density 0.035%

    No Known Activations