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

    Neuronpedia

    INDEX
    Explanations

    references to various types of roads and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESA
    -0.16
    /tos
    -0.16
    erialize
    -0.16
    cip
    -0.16
    ment
    -0.15
    uka
    -0.15
    inerary
    -0.15
    sek
    -0.15
    missive
    -0.14
    OfWork
    -0.14
    POSITIVE LOGITS
    ways
    0.32
    stead
    0.26
    side
    0.23
    blocks
    0.23
    kill
    0.22
    runner
    0.21
    ides
    0.20
     leading
    0.20
    /high
    0.19
    bed
    0.19
    Act Density 0.046%

    No Known Activations