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

    Neuronpedia

    INDEX
    Explanations

    terms related to construction and structural attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maal
    -0.18
    iao
    -0.18
    iasi
    -0.17
    ea
    -0.15
    antanamo
    -0.15
    729
    -0.15
    773
    -0.15
    eração
    -0.14
    beck
    -0.14
    een
    -0.14
    POSITIVE LOGITS
    uir
    0.35
    uido
    0.28
    uire
    0.28
    uida
    0.28
    uite
    0.26
    uÃŃ
    0.24
    uyo
    0.23
    uy
    0.23
    uis
    0.22
    uye
    0.22
    Act Density 0.015%

    No Known Activations