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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social and environmental responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æŃ
    -0.15
    forge
    -0.15
    ORK
    -0.15
    Forge
    -0.14
    argent
    -0.13
    nock
    -0.13
    arend
    -0.13
    iente
    -0.13
    nement
    -0.13
     tym
    -0.13
    POSITIVE LOGITS
    łĢ
    0.18
     Transparency
    0.16
    orca
    0.16
    actice
    0.15
     transparency
    0.15
    hero
    0.15
     DAO
    0.14
    asio
    0.14
    ulty
    0.14
    olulu
    0.14
    Act Density 0.029%

    No Known Activations