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

    Neuronpedia

    INDEX
    Explanations

    references to official statements or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     importance
    -0.18
    uptools
    -0.17
     Importance
    -0.17
    ê¸ī
    -0.15
    iode
    -0.15
    ackets
    -0.14
    uent
    -0.14
    iets
    -0.14
    инки
    -0.14
    iddet
    -0.14
    POSITIVE LOGITS
    .go
    0.19
     Go
    0.18
     go
    0.18
    	go
    0.18
    .GO
    0.18
    (go
    0.17
    Go
    0.17
    go
    0.16
     Benchmark
    0.16
    eken
    0.16
    Act Density 0.050%

    No Known Activations