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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantities and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ολ
    -0.16
    ANDOM
    -0.15
    ile
    -0.15
    ý
    -0.14
    eltas
    -0.14
    venues
    -0.14
    OLA
    -0.14
    ola
    -0.14
    otos
    -0.14
    \CMS
    -0.14
    POSITIVE LOGITS
     syll
    0.18
     times
    0.18
     fewer
    0.17
     steps
    0.17
     altogether
    0.16
    745
    0.15
    asty
    0.15
    ossa
    0.15
    ieder
    0.15
     votes
    0.15
    Act Density 0.103%

    No Known Activations