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

    Neuronpedia

    INDEX
    Explanations

    technical terms and symbols related to statistical models and mathematical representations

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

    mathematical notation and formatting symbols in academic or scientific documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    <unused43>
    -0.70
    <unused16>
    -0.70
    <unused17>
    -0.70
    <unused14>
    -0.70
    <unused28>
    -0.70
    <unused51>
    -0.70
    <unused41>
    -0.70
    <unused74>
    -0.70
    <unused3>
    -0.69
    <unused8>
    -0.69
    POSITIVE LOGITS
    enumi
    0.57
    AnimationsModule
    0.49
     ""],
    0.47
     defaultstate
    0.46
    AutoScale
    0.44
    ↵↵↵
    0.43
    isContained
    0.43
    BagConstraints
    0.41
    ↵
    0.41
    MathML
    0.41
    Act Density 2.184%

    No Known Activations