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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values, particularly related to age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    11
    -0.17
    12
    -0.17
    /REC
    -0.17
    16
    -0.16
    13
    -0.16
    ieber
    -0.16
    32
    -0.15
    10
    -0.15
     Hundred
    -0.15
    irim
    -0.15
    POSITIVE LOGITS
    -two
    0.44
    -five
    0.40
    -four
    0.39
    -three
    0.39
    -one
    0.39
    -six
    0.35
    -seven
    0.35
    -eight
    0.34
    -nine
    0.33
    -first
    0.29
    Act Density 0.031%

    No Known Activations