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

    Neuronpedia

    INDEX
    Explanations

    references to time periods or phases within historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongs
    -0.15
     handicap
    -0.15
    965
    -0.15
     weakness
    -0.15
    motion
    -0.15
    BUF
    -0.14
    çīĩ
    -0.14
    rnek
    -0.14
    æĸ¹éĿ¢
    -0.14
    und
    -0.14
    POSITIVE LOGITS
    veis
    0.18
    /end
    0.17
    ãĤ¯ãĥĪ
    0.15
    orse
    0.15
    ereço
    0.15
    owment
    0.15
    /start
    0.15
    weit
    0.15
    rowned
    0.15
     каждого
    0.15
    Act Density 0.029%

    No Known Activations