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

    Neuronpedia

    INDEX
    Explanations

    references to roads and related infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OfDay
    -0.16
    ment
    -0.15
    MENT
    -0.15
    aad
    -0.15
    OfWork
    -0.15
    /tos
    -0.15
    erialize
    -0.15
    cip
    -0.15
    ESA
    -0.14
    dto
    -0.14
    POSITIVE LOGITS
    ways
    0.38
    stead
    0.30
     leading
    0.26
    blocks
    0.25
    kill
    0.23
    WAYS
    0.23
    leading
    0.23
    bed
    0.23
    Leading
    0.22
    side
    0.22
    Act Density 0.037%

    No Known Activations