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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition or popularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kte
    -0.18
    annies
    -0.15
    enia
    -0.15
    ker
    -0.15
    .vaadin
    -0.14
     spot
    -0.14
    achable
    -0.14
    elight
    -0.14
     recip
    -0.13
    ÑŁ
    -0.13
    POSITIVE LOGITS
    λικά
    0.17
    558
    0.16
    ynn
    0.15
    ãĥ¼ãĤ¹ãĥĪ
    0.15
    lessly
    0.15
    arily
    0.15
    ìŀ
    0.15
    ially
    0.15
    677
    0.14
     sobie
    0.14
    Act Density 0.040%

    No Known Activations