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

    Neuronpedia

    INDEX
    Explanations

    descriptions or technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    segments labeled as "Description" or similar informational categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    driving
    -0.73
    ipping
    -0.70
    lling
    -0.68
    raf
    -0.68
    soDeliveryDate
    -0.65
    zag
    -0.64
     labour
    -0.64
    aded
    -0.63
    gue
    -0.62
    ulously
    -0.61
    POSITIVE LOGITS
     Features
    0.97
     Details
    0.95
     Overview
    0.90
     Definition
    0.88
     Summary
    0.86
     Description
    0.86
     Differences
    0.85
     Edit
    0.83
     Languages
    0.82
     References
    0.82
    Act Density 0.095%

    No Known Activations