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

    Neuronpedia

    INDEX
    Explanations

    key terms and identifiers related to specific organizations, products, or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĥла
    -0.14
    "default
    -0.14
    alan
    -0.14
    ahren
    -0.14
     elder
    -0.14
    aub
    -0.14
    egan
    -0.13
    eld
    -0.13
    ÅĤo
    -0.13
     Moran
    -0.13
    POSITIVE LOGITS
    ottle
    0.16
    reich
    0.15
    urrent
    0.15
    urgy
    0.15
    ompiler
    0.14
    utherland
    0.14
    _ABI
    0.14
    .legend
    0.14
    ãĥ³ãĥij
    0.14
    agit
    0.13
    Act Density 0.015%

    No Known Activations