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

    Neuronpedia

    INDEX
    Explanations

    terminology related to stewardship and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nem
    -0.15
    ابÙĬ
    -0.15
     Kata
    -0.15
    AI
    -0.15
    arro
    -0.14
    ai
    -0.14
    оÑı
    -0.14
    353
    -0.14
    ortal
    -0.14
    akte
    -0.13
    POSITIVE LOGITS
    碼
    0.16
    atz
    0.15
    itory
    0.15
    (æľ¨
    0.15
    oop
    0.15
    .skin
    0.14
    ships
    0.14
    .appspot
    0.14
    ãĤ´ãĥª
    0.14
    ship
    0.14
    Act Density 0.012%

    No Known Activations