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

    Neuronpedia

    INDEX
    Explanations

    file-related terms or directives, such as creating, compiling, or naming files

    oai_token-act-pair · gpt-3.5-turbo

    mentions of files in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anson
    -0.86
    ĵĺ
    -0.84
    sylvania
    -0.80
    ão
    -0.74
    apo
    -0.71
    osate
    -0.70
     Rohing
    -0.69
    pter
    -0.68
    iership
    -0.68
     Azerb
    -0.66
    POSITIVE LOGITS
    Upload
    1.04
    ystem
    1.01
     descriptor
    0.96
    ettes
    0.95
    types
    0.92
     upload
    0.88
    copy
    0.86
    ette
    0.84
     descript
    0.81
     Upload
    0.81
    Act Density 0.023%

    No Known Activations