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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Lang" or variations thereof, possibly indicating a focus on language or specific coding functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fant
    -0.16
    ãĥ£
    -0.16
    oux
    -0.16
    ants
    -0.15
    ategorical
    -0.15
    лика
    -0.15
    uding
    -0.14
     ç¤
    -0.14
    esan
    -0.14
    osl
    -0.13
    POSITIVE LOGITS
    auge
    0.25
    AFX
    0.18
    sam
    0.17
    ford
    0.17
    .reflect
    0.17
    .invoke
    0.17
    ley
    0.16
    affe
    0.16
    don
    0.16
    .stride
    0.16
    Act Density 0.011%

    No Known Activations