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

    Neuronpedia

    INDEX
    Explanations

    references to numeric values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuff
    -0.15
     Numerous
    -0.15
    eter
    -0.15
     Thousands
    -0.15
    許
    -0.15
     thousands
    -0.14
    s
    -0.14
    olls
    -0.14
    mates
    -0.14
    stuff
    -0.14
    POSITIVE LOGITS
    fold
    0.27
    teenth
    0.26
     different
    0.24
    -legged
    0.21
    -dimensional
    0.20
    eenth
    0.20
    -digit
    0.20
     separate
    0.19
     dozen
    0.19
     additional
    0.19
    Act Density 0.185%

    No Known Activations