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

    Neuronpedia

    INDEX
    Explanations

    terms related to changes and modifications in data or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chem
    -0.17
    ë¦Ħ
    -0.15
    .Guna
    -0.15
    é¡¿
    -0.14
    ãĥ¼ãĥģ
    -0.14
    joint
    -0.14
    ÑĢÑıдÑĥ
    -0.14
    à¥Ĥद
    -0.14
    åį
    -0.13
    Ĩµ
    -0.13
    POSITIVE LOGITS
    ura
    0.15
    uren
    0.14
    ãĥ³ãĤ¯
    0.14
    -educated
    0.14
     Volk
    0.14
    Content
    0.14
    elmet
    0.14
     operator
    0.14
    gesch
    0.13
    nce
    0.13
    Act Density 0.050%

    No Known Activations