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

    Neuronpedia

    INDEX
    Explanations

    variations of data types in a structured data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ([↵
    -0.20
    :[[
    -0.18
    ][(
    -0.17
    Poster
    -0.17
    =[[
    -0.16
    ][-
    -0.16
     dele
    -0.16
     ([]
    -0.15
    )[-
    -0.15
    ([-
    -0.15
    POSITIVE LOGITS
     [
    0.28
     Roe
    0.17
    [
    0.17
    ackson
    0.15
    ansi
    0.15
    isObject
    0.15
    _OCCURRED
    0.15
    sparse
    0.14
    dna
    0.14
    \[
    0.14
    Act Density 0.079%

    No Known Activations