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

    Neuronpedia

    INDEX
    Explanations

    significant words that indicate complexity, connection, or importance in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     accompanying
    -0.18
    anten
    -0.16
     progress
    -0.16
     either
    -0.15
    /Runtime
    -0.15
     accompany
    -0.14
     sow
    -0.14
     advance
    -0.14
     associate
    -0.14
    ine
    -0.13
    POSITIVE LOGITS
    enza
    0.16
    _collect
    0.15
    /original
    0.14
     Gathering
    0.14
     orig
    0.14
    ToProps
    0.14
     sourcing
    0.14
    ÑĨеп
    0.14
     Signing
    0.13
     Attribution
    0.13
    Act Density 0.029%

    No Known Activations