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

    Neuronpedia

    INDEX
    Explanations

    code snippets or programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    syntax elements and functions used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sov
    -0.95
     unpop
    -0.75
    Ku
    -0.73
    MpServer
    -0.73
    pees
    -0.70
    ocaust
    -0.68
    Hunt
    -0.67
    kefeller
    -0.67
    ebook
    -0.67
    yg
    -0.66
    POSITIVE LOGITS
    (){
    0.90
     __
    0.82
    ():
    0.72
     ()
    0.70
    duration
    0.68
     const
    0.67
     bool
    0.67
     initialize
    0.66
     args
    0.66
    Dispatch
    0.65
    Act Density 0.071%

    No Known Activations