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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical relationships and structures within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rowse
    -0.15
    Pairs
    -0.15
    452
    -0.15
    shint
    -0.15
    -valu
    -0.14
    ç¿Ĵ
    -0.14
    ubit
    -0.13
    .ToShort
    -0.13
    paired
    -0.13
    pairs
    -0.13
    POSITIVE LOGITS
     depth
    0.38
     Depth
    0.35
     children
    0.34
    Depth
    0.34
    depth
    0.34
    _depth
    0.34
     child
    0.34
     deeper
    0.32
    -depth
    0.31
     childs
    0.31
    Act Density 0.533%

    No Known Activations