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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Benchmark
    -0.16
     Bench
    -0.16
    浦
    -0.15
     benchmarks
    -0.15
     Benchmark
    -0.14
    benchmark
    -0.14
    uj
    -0.14
    кав
    -0.13
     bench
    -0.13
     sob
    -0.13
    POSITIVE LOGITS
     semantics
    0.25
     behavior
    0.22
    gran
    0.19
     representation
    0.19
     meaning
    0.19
     gran
    0.19
     behaviour
    0.19
     Gran
    0.18
    antics
    0.18
     contract
    0.18
    Act Density 0.362%

    No Known Activations