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

    Neuronpedia

    INDEX
    Explanations

    files or file-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to files and their naming conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sylvania
    -0.86
    anson
    -0.81
    ĵĺ
    -0.76
    apo
    -0.70
    osate
    -0.69
     Azerb
    -0.69
    ão
    -0.67
     Rohing
    -0.67
    iership
    -0.66
    ardon
    -0.65
    POSITIVE LOGITS
    ystem
    1.01
     descriptor
    1.01
    Upload
    1.01
    ettes
    0.97
     upload
    0.93
    ette
    0.88
    copy
    0.87
    types
    0.86
     (.
    0.85
    handle
    0.85
    Act Density 0.024%

    No Known Activations