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

    Neuronpedia

    INDEX
    Explanations

    terms related to hierarchical structures or classifications

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

    hierarchical structure and groupings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spann
    -0.53
    ment
    -0.51
     McCra
    -0.50
     Chriftian
    -0.48
     pleaſure
    -0.47
     myſelf
    -0.46
    mergeFrom
    -0.45
    Donnell
    -0.45
     uſed
    -0.45
    addComponent
    -0.44
    POSITIVE LOGITS
     hier
    1.70
     Hier
    1.65
    Hier
    1.63
    hier
    1.35
     HIER
    1.31
     hierarchies
    1.07
    HIER
    1.06
     hiér
    0.97
     hierarchy
    0.97
    Hierarchy
    0.95
    Act Density 0.005%

    No Known Activations