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

    Neuronpedia

    INDEX
    Explanations

    elements related to hierarchical data structures and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rowse
    -0.15
    beck
    -0.15
    ariat
    -0.14
     sped
    -0.14
    452
    -0.14
    Pairs
    -0.14
     gab
    -0.14
    shint
    -0.13
     DateFormatter
    -0.13
     stoi
    -0.13
    POSITIVE LOGITS
     tree
    0.45
     Tree
    0.40
    tree
    0.39
     depth
    0.39
     leaf
    0.38
     Depth
    0.36
    Depth
    0.36
    _tree
    0.36
    _depth
    0.36
    Tree
    0.35
    Act Density 0.479%

    No Known Activations