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

    Neuronpedia

    INDEX
    Explanations

    factual statements regarding conditions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uche
    -0.16
    ç¿Ķ
    -0.14
     Mell
    -0.14
    rouch
    -0.13
    arc
    -0.13
    inson
    -0.13
    IPA
    -0.13
     Ir
    -0.13
     Wh
    -0.13
    ãĤīãģı
    -0.13
    POSITIVE LOGITS
    ElementsBy
    0.17
    ehr
    0.15
    \Domain
    0.15
    gere
    0.14
    buquerque
    0.14
     Ùħات
    0.14
    aban
    0.14
    umi
    0.14
    Evaluator
    0.14
    ()?>
    0.13
    Act Density 0.208%

    No Known Activations