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

    Neuronpedia

    INDEX
    Explanations

    words related to financial benchmarks or standards

    oai_token-act-pair · gpt-3.5-turbo

    references to benchmarks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pod
    -0.72
     Ung
    -0.69
    radio
    -0.69
     Char
    -0.68
     slips
    -0.67
     Gott
    -0.67
     voic
    -0.66
     plates
    -0.66
    letters
    -0.64
    UU
    -0.63
    POSITIVE LOGITS
     benchmark
    3.91
     benchmarks
    2.98
    Bench
    1.91
     Bench
    1.86
    bench
    1.68
     milestone
    1.09
     overcl
    1.06
     metrics
    1.06
     comparison
    1.04
     comparisons
    0.99
    Act Density 0.024%

    No Known Activations