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

    Neuronpedia

    INDEX
    Explanations

    terms related to combining or uniting entities or elements

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of merging or integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zero
    -0.71
    den
    -0.71
    nic
    -0.70
    sk
    -0.70
    acco
    -0.67
    null
    -0.66
    dain
    -0.65
    eq
    -0.65
    sol
    -0.64
    demand
    -0.64
    POSITIVE LOGITS
     merging
    1.23
     merge
    1.23
     merged
    1.01
     merger
    0.99
    halla
    0.86
     amalg
    0.78
     redund
    0.74
    essional
    0.74
     seamlessly
    0.71
    itational
    0.71
    Act Density 0.012%

    No Known Activations