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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warts
    -0.19
    Ī¬
    -0.15
     Priv
    -0.15
    504
    -0.15
    ské
    -0.15
    variant
    -0.14
    pell
    -0.14
    úb
    -0.14
    acre
    -0.14
    TURE
    -0.14
    POSITIVE LOGITS
    Fallback
    0.14
     marque
    0.14
    odata
    0.14
     erót
    0.14
     @}
    0.14
    AZY
    0.13
     unfavor
    0.13
    oise
    0.13
    çŀ
    0.13
    exter
    0.13
    Act Density 0.006%

    No Known Activations