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

    Neuronpedia

    INDEX
    Explanations

    tokens related to numerical data and specific identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.20
    onis
    -0.17
    ething
    -0.15
    strup
    -0.15
    cente
    -0.14
    дем
    -0.14
    á»Ļc
    -0.14
    aria
    -0.14
    ichni
    -0.13
    ResourceManager
    -0.13
    POSITIVE LOGITS
     window
    0.20
     Mer
    0.19
    mer
    0.19
     mer
    0.19
     Lane
    0.17
    Mer
    0.17
     windows
    0.17
     MER
    0.17
    MER
    0.17
    window
    0.17
    Act Density 0.006%

    No Known Activations