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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical theorems or sections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUEST
    -0.17
    ãĥ³ãĥIJ
    -0.15
    ãĥ«ãĤ¯
    -0.14
    rvé
    -0.13
    ema
    -0.13
    cimal
    -0.13
    缮ãĤĴ
    -0.13
    rum
    -0.13
    umbo
    -0.13
    ood
    -0.13
    POSITIVE LOGITS
     forb
    0.15
    ufs
    0.15
    ledi
    0.14
    лоп
    0.14
    ï¸ı
    0.14
    166
    0.14
    orsi
    0.13
    093
    0.13
    747
    0.13
    ecies
    0.13
    Act Density 0.026%

    No Known Activations