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

    Neuronpedia

    INDEX
    Explanations

    references to time durations, specifically years and decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifelong
    -0.16
    mt
    -0.15
    ira
    -0.15
     overnight
    -0.15
     forever
    -0.15
     за
    -0.15
    191
    -0.15
     lasting
    -0.15
    186
    -0.15
     пÑĢоÑĤÑıгом
    -0.15
    POSITIVE LOGITS
     ÙħÛĮÙĦادÛĮ
    0.17
     ago
    0.16
    .Tween
    0.15
    ãĥĵãĥ¼
    0.15
     é¦
    0.15
    upert
    0.15
    acer
    0.15
    .pg
    0.14
    adt
    0.14
    alamat
    0.14
    Act Density 0.065%

    No Known Activations