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

    Neuronpedia

    INDEX
    Explanations

    references to prices and costs associated with services or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sposób
    -0.18
    /values
    -0.17
    hek
    -0.17
     timed
    -0.16
    conti
    -0.16
    uren
    -0.15
    tem
    -0.15
    äge
    -0.15
    Äĥng
    -0.15
    way
    -0.14
    POSITIVE LOGITS
     amount
    0.25
     total
    0.25
     figure
    0.23
     maximum
    0.23
     minimum
    0.23
     average
    0.22
     expected
    0.22
     theoretical
    0.21
     sum
    0.21
     number
    0.20
    Act Density 0.280%

    No Known Activations