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

    Neuronpedia

    INDEX
    Explanations

    terms related to performance metrics and benchmarking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     au
    -0.47
    uska
    -0.47
    Portail
    -0.46
    erà
    -0.45
    CrossOrigin
    -0.45
     cesta
    -0.43
    gis
    -0.41
    бу
    -0.41
     успешно
    -0.40
    Presenters
    -0.40
    POSITIVE LOGITS
     benchmarks
    0.93
    benchmark
    0.91
     benchmarking
    0.89
     benchmark
    0.86
    Bench
    0.83
     Benchmark
    0.83
    bench
    0.80
    Benchmark
    0.80
     bench
    0.79
     Bench
    0.77
    Act Density 1.046%

    No Known Activations