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

    Neuronpedia

    INDEX
    Explanations

    references to topics or subjects within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StrictEqual
    -0.77
     sedentary
    -0.69
    halb
    -0.68
    <blockquote>
    -0.65
    <h6>
    -0.65
    createServer
    -0.62
    crose
    -0.59
     Barrera
    -0.59
     ■
    -0.58
    tras
    -0.58
    POSITIVE LOGITS
     topics
    1.74
     TOPIC
    1.69
     topic
    1.64
     Topic
    1.63
     Topics
    1.58
    topics
    1.56
    Topics
    1.55
    topic
    1.52
    Topic
    1.48
    TOPIC
    1.43
    Act Density 0.061%

    No Known Activations