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

    Neuronpedia

    INDEX
    Explanations

    terms related to imperfections or shortcomings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    «
    -0.15
    ाà¤ĸ
    -0.15
    âng
    -0.15
     bloginfo
    -0.14
    kte
    -0.14
    layui
    -0.14
    utters
    -0.14
    ãģįãģŁ
    -0.14
    гоÑĢ
    -0.14
    Rpc
    -0.13
    POSITIVE LOGITS
    622
    0.15
    fram
    0.15
     NL
    0.14
    tplib
    0.14
    acco
    0.14
    عداد
    0.14
     Torch
    0.14
    NL
    0.13
    445
    0.13
    Internet
    0.13
    Act Density 0.003%

    No Known Activations