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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to performance benchmarks and evaluation in robotics and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chy
    -0.17
     casting
    -0.15
     Marr
    -0.15
     Shan
    -0.15
    kazy
    -0.14
     cast
    -0.14
     Reviews
    -0.14
    ernals
    -0.13
     Mara
    -0.13
    alendar
    -0.13
    POSITIVE LOGITS
     benchmark
    0.29
     bench
    0.29
     Benchmark
    0.28
    Benchmark
    0.28
    bench
    0.28
     Bench
    0.28
    benchmark
    0.27
     benchmarks
    0.26
     run
    0.24
     benches
    0.24
    Act Density 0.072%

    No Known Activations