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

    Neuronpedia

    INDEX
    Explanations

    concepts related to reinforcement learning and its detailed mathematical formulation

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

    discounted value maximization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.33
     symbol
    -0.29
     variables
    -0.28
    ,
    -0.28
     
    -0.27
    ↵↵
    -0.26
    ↵↵↵↵
    -0.25
     enough
    -0.25
     Fe
    -0.25
     men
    -0.25
    POSITIVE LOGITS
    EndGlobalSection
    0.77
    <unused16>
    0.71
    <unused8>
    0.71
    [@BOS@]
    0.70
    <unused41>
    0.70
    <unused17>
    0.70
    <unused28>
    0.70
    <unused23>
    0.70
    <unused3>
    0.70
    <unused14>
    0.70
    Act Density 0.391%

    No Known Activations