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

    Neuronpedia

    INDEX
    Explanations

    references to related sections or topics in a text

    oai_token-act-pair · gpt-3.5-turbo

    formatted references and citations within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.60
     bottleneck
    -0.60
     mindset
    -0.58
    fitted
    -0.56
    iameter
    -0.56
     hous
    -0.56
     mosqu
    -0.55
     dominating
    -0.55
    Introduced
    -0.54
    Mesh
    -0.53
    POSITIVE LOGITS
    References
    0.95
    âĨij
    0.94
     Encyclopedia
    0.83
    ibliography
    0.80
     references
    0.79
    reference
    0.76
     citation
    0.76
    Reference
    0.75
     References
    0.75
    Appearances
    0.72
    Act Density 0.068%

    No Known Activations