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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms related to functions and parameters

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to parameters and arguments in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.81
    rup
    -0.75
    kus
    -0.72
     Bras
    -0.68
    icago
    -0.68
    velt
    -0.67
    tics
    -0.66
    shit
    -0.64
     millenn
    -0.64
    chron
    -0.64
    POSITIVE LOGITS
    eters
    1.06
     parameter
    0.98
     parameters
    0.94
     specifying
    0.93
    eter
    0.92
     specifies
    0.92
     args
    0.90
     values
    0.89
     params
    0.88
     validation
    0.85
    Act Density 0.041%

    No Known Activations