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

    Neuronpedia

    INDEX
    Explanations

    concepts related to benchmarking and performance evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enco
    -0.18
    chy
    -0.15
    eln
    -0.14
     Mara
    -0.14
     Reviews
    -0.14
     reviews
    -0.14
     Marr
    -0.14
    eus
    -0.14
    åĥį
    -0.14
    erman
    -0.13
    POSITIVE LOGITS
     benchmark
    0.28
     Benchmark
    0.28
     bench
    0.28
    Benchmark
    0.27
    bench
    0.27
    benchmark
    0.26
     Bench
    0.25
     benchmarks
    0.25
     benches
    0.23
     run
    0.20
    Act Density 0.050%

    No Known Activations