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

    Neuronpedia

    INDEX
    Explanations

    statements of personal reflection or opinion

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

    past thoughts and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endblock
    -0.33
    XtraBars
    -0.31
    AsUp
    -0.30
     thanks
    -0.29
    {}'.
    -0.29
     lucro
    -0.29
     zufolge
    -0.28
     дії
    -0.28
     gants
    -0.28
    ของคุณ
    -0.28
    POSITIVE LOGITS
     thought
    1.18
    Thought
    1.16
     Thought
    1.11
     THOUGHT
    1.10
    thought
    1.10
     AssemblyTitle
    0.82
     dachte
    0.74
     tưởng
    0.71
    SequentialGroup
    0.70
     dacht
    0.68
    Act Density 0.015%

    No Known Activations