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

    Neuronpedia

    INDEX
    Explanations

    references to performance metrics and comparisons in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oub
    -0.15
    eln
    -0.15
    fty
    -0.15
    ynet
    -0.15
    rus
    -0.14
     caster
    -0.14
    eÄį
    -0.14
    ãģ£ãģį
    -0.14
    udd
    -0.14
     epid
    -0.14
    POSITIVE LOGITS
     benchmark
    0.41
    Benchmark
    0.39
     Benchmark
    0.38
     benchmarks
    0.38
    bench
    0.38
     bench
    0.37
    benchmark
    0.36
     Bench
    0.35
     benches
    0.32
     performance
    0.23
    Act Density 0.007%

    No Known Activations