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

    Neuronpedia

    INDEX
    Explanations

    phrases related to educational topics, especially focusing on the concept of learning

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psc
    -0.66
     Skydragon
    -0.64
    iso
    -0.62
    sburg
    -0.62
     Syndicate
    -0.61
     designate
    -0.60
    flag
    -0.60
    allow
    -0.59
     Slim
    -0.59
     Outer
    -0.59
    POSITIVE LOGITS
     learning
    3.80
    learning
    2.98
     Learning
    2.66
    Learning
    2.47
    learn
    2.07
     learners
    2.00
     learn
    1.95
     lear
    1.86
     learned
    1.65
     learns
    1.65
    Act Density 0.017%

    No Known Activations