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

    Neuronpedia

    INDEX
    Explanations

    terms related to efficiency and optimization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    foundland
    -0.16
    antha
    -0.16
    -thirds
    -0.16
    ème
    -0.16
    ruba
    -0.15
    upon
    -0.14
    usz
    -0.14
    -fashioned
    -0.14
    FFFFFFFF
    -0.14
    figur
    -0.14
    POSITIVE LOGITS
    çİĩ
    0.26
    iciency
    0.20
    /product
    0.19
    /e
    0.18
    icient
    0.18
    iy
    0.17
    eenth
    0.16
    aly
    0.16
     gains
    0.16
    tl
    0.16
    Act Density 0.037%

    No Known Activations