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

    Neuronpedia

    INDEX
    Explanations

    terms related to hierarchical structures and systems

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

    hierarchical structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pepper
    -0.47
     NIT
    -0.45
     opium
    -0.45
    alnız
    -0.45
     Opium
    -0.44
    colgroup
    -0.44
    rael
    -0.44
    TestId
    -0.43
     Trix
    -0.43
    vent
    -0.43
    POSITIVE LOGITS
     hierarchical
    1.63
     hiér
    1.60
     Hierarchical
    1.52
     hierarchy
    1.49
     Hierarchy
    1.45
    Hierarchical
    1.43
     hierarchies
    1.39
    Hierarchy
    1.38
     hierarch
    1.34
    hierarchy
    1.30
    Act Density 0.014%

    No Known Activations