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

    Neuronpedia

    INDEX
    Explanations

    system file paths

    oai_token-act-pair · gpt-3.5-turbo

    file paths in a system or code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Archdemon
    -0.82
     TAMADRA
    -0.81
     Mace
    -0.76
     Carlton
    -0.74
     Duchess
    -0.73
     Bridgewater
    -0.72
     Proposition
    -0.72
     warranted
    -0.70
     Alchemist
    -0.70
     Gamble
    -0.70
    POSITIVE LOGITS
    modules
    1.17
    local
    1.17
    lib
    1.13
    rc
    1.10
    environment
    1.10
    default
    1.08
    pmwiki
    1.06
    sites
    1.04
    console
    1.03
    apache
    1.01
    Act Density 0.030%

    No Known Activations