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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of originality or original works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipo
    -0.16
     mere
    -0.15
     toward
    -0.14
    oons
    -0.14
    into
    -0.14
    ep
    -0.14
     terk
    -0.14
    ib
    -0.14
    æĬ¼
    -0.14
    4
    -0.14
    POSITIVE LOGITS
    reten
    0.17
    mez
    0.15
    trx
    0.15
    _hooks
    0.14
     Predictor
    0.14
    omid
    0.14
     gá»ijc
    0.14
    idar
    0.14
    WindowSize
    0.14
    алов
    0.14
    Act Density 0.014%

    No Known Activations