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

    Neuronpedia

    INDEX
    Explanations

    references to debates or discussions on specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    debate and discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kingston
    -0.65
    Kingston
    -0.64
     numberWith
    -0.57
    Pherson
    -0.56
     uncin
    -0.52
     kasarigan
    -0.50
    getManager
    -0.49
    Nicholas
    -0.49
     Wilmington
    -0.49
     Infinity
    -0.48
    POSITIVE LOGITS
     debate
    1.21
     Debate
    1.14
    debate
    1.13
    Debate
    1.02
     debates
    1.02
     debated
    0.99
     Debates
    0.96
     debating
    0.88
     DEB
    0.84
     débats
    0.83
    Act Density 0.006%

    No Known Activations