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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to benchmarks and performance metrics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    nehå
    -0.73
     générations
    -0.65
     tourné
    -0.63
     régiment
    -0.62
     autocollant
    -0.61
     rispond
    -0.60
    Ārējās
    -0.59
    typescript
    -0.59
     sesso
    -0.59
     poto
    -0.58
    POSITIVE LOGITS
     Bench
    1.52
     bench
    1.47
     benchmark
    1.37
    Bench
    1.36
     benchmarks
    1.34
    bench
    1.30
     Benchmark
    1.30
    BENCH
    1.25
    benchmark
    1.22
     benches
    1.20
    Act Density 0.002%

    No Known Activations