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

    Neuronpedia

    INDEX
    Explanations

    numerical references and quantifications related to counts, especially those emphasizing groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.17
    olls
    -0.17
    eter
    -0.16
    s
    -0.15
    enas
    -0.15
    stå
    -0.14
    stuff
    -0.14
    icens
    -0.13
    ummings
    -0.13
    tems
    -0.12
    POSITIVE LOGITS
    fold
    0.27
     different
    0.23
    -fold
    0.22
    teenth
    0.22
    ancy
    0.21
    -dimensional
    0.20
    eenth
    0.18
    -legged
    0.18
    -digit
    0.18
    acity
    0.17
    Act Density 0.199%

    No Known Activations