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

    Neuronpedia

    INDEX
    Explanations

    references to weight measurements, specifically pounds and kilograms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finder
    -0.15
    angelo
    -0.15
    inde
    -0.14
    ξ
    -0.14
    828
    -0.14
    inar
    -0.13
     autob
    -0.13
    acd
    -0.13
    o
    -0.13
     commande
    -0.13
    POSITIVE LOGITS
     weight
    0.21
    weight
    0.20
    -weight
    0.19
     weights
    0.18
    weights
    0.18
    .weight
    0.18
    (weight
    0.18
    pii
    0.17
    Weights
    0.17
    Weight
    0.17
    Act Density 0.025%

    No Known Activations