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

    Neuronpedia

    INDEX
    Explanations

    software programming-related terms or snippets of code

    oai_token-act-pair · gpt-3.5-turbo

    references to programming classes and their methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.76
    egal
    -0.69
    waters
    -0.68
    fare
    -0.68
    andum
    -0.66
    iverpool
    -0.65
    llah
    -0.65
    hiba
    -0.64
     videot
    -0.63
    antz
    -0.63
    POSITIVE LOGITS
     namespace
    1.02
     {}
    0.95
     constructor
    0.94
     Foo
    0.93
    classes
    0.93
     syntax
    0.90
     lookup
    0.87
     parameter
    0.87
     foo
    0.87
     API
    0.86
    Act Density 0.134%

    No Known Activations