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

    Neuronpedia

    INDEX
    Explanations

    references to real and imaginary components in complex data or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dientemente
    -0.69
     recommandons
    -0.64
    modelBuilder
    -0.63
    PILE
    -0.54
    riwal
    -0.53
     Hampden
    -0.53
    RenderAtEndOf
    -0.52
    UMBUS
    -0.52
     AssemblyProduct
    -0.51
     dég
    -0.51
    POSITIVE LOGITS
     real
    1.89
     vraie
    1.09
     réel
    1.07
    real
    1.06
     reales
    1.06
     echte
    1.06
     réelle
    1.05
     реаль
    1.03
     vrai
    0.98
     reale
    0.96
    Act Density 0.075%

    No Known Activations