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

    Neuronpedia

    INDEX
    Explanations

    concepts related to system efficiencies and safety improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llum
    -0.17
    ,LOCATION
    -0.15
    angu
    -0.14
    fon
    -0.14
     Brendan
    -0.14
     domic
    -0.13
    .Utility
    -0.13
    utan
    -0.13
    azon
    -0.13
    rend
    -0.13
    POSITIVE LOGITS
     CA
    0.30
     simulation
    0.28
     Simulation
    0.26
     FE
    0.25
    simulation
    0.24
     solver
    0.24
     simulations
    0.23
    Simulation
    0.23
    CA
    0.23
     finite
    0.22
    Act Density 0.007%

    No Known Activations