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

    Neuronpedia

    INDEX
    Explanations

    components related to complexity and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.64
    edBy
    -0.37
    i
    -0.37
    a
    -0.35
    ÛĮ
    -0.35
    er
    -0.32
    edn
    -0.30
    ãĤ§
    -0.29
    edl
    -0.27
    à¸Ļ
    -0.27
    POSITIVE LOGITS
    tempts
    0.21
    íĬ¹ë³Ħìĭľ
    0.20
    onical
    0.20
    inition
    0.19
    ments
    0.19
    otros
    0.19
    ÑįÑĤомÑĥ
    0.19
    entication
    0.18
    ness
    0.18
    ร
    0.18
    Act Density 1.138%

    No Known Activations