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

    Neuronpedia

    INDEX
    Explanations

    file paths and code snippets in a programming environment

    oai_token-act-pair · gpt-3.5-turbo

    file path and directory structure terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     soaring
    -0.72
     Obi
    -0.70
     Archdemon
    -0.68
     Arkansas
    -0.68
     Illinois
    -0.67
     swat
    -0.67
     Mercy
    -0.67
     clin
    -0.66
     Samar
    -0.65
     Elliott
    -0.65
    POSITIVE LOGITS
    default
    1.14
    src
    1.11
    etc
    1.08
    modules
    1.08
    Library
    1.06
    input
    1.06
    library
    1.05
    tmp
    1.01
    console
    1.00
    misc
    0.99
    Act Density 0.049%

    No Known Activations