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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "one" in various contexts and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lob
    -0.19
    cke
    -0.15
    ANG
    -0.14
    =logging
    -0.14
    кеÑĤ
    -0.13
    mos
    -0.13
     UIGraphics
    -0.13
    atern
    -0.13
     Wert
    -0.13
    :return
    -0.13
    POSITIVE LOGITS
    oty
    0.17
     Genre
    0.17
    agne
    0.16
    atown
    0.16
    ÏĦιο
    0.15
    iveness
    0.14
    resses
    0.14
    rahim
    0.14
    ascade
    0.14
    kat
    0.14
    Act Density 0.087%

    No Known Activations