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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.16
     Bilim
    -0.14
    ackages
    -0.14
    кап
    -0.14
    ayscale
    -0.14
    layui
    -0.14
     Stake
    -0.13
    .getvalue
    -0.13
     Ster
    -0.13
     Bris
    -0.13
    POSITIVE LOGITS
     Cla
    0.15
    ulla
    0.15
    plies
    0.15
    aska
    0.14
    ill
    0.14
    461
    0.14
    arks
    0.14
    urum
    0.13
    ASE
    0.13
    .Collection
    0.13
    Act Density 0.034%

    No Known Activations