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

    Neuronpedia

    INDEX
    Explanations

    terms related to uniformity and standardization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.17
    ammer
    -0.17
    rome
    -0.16
    anke
    -0.16
    osu
    -0.15
    anki
    -0.15
    ноÑĪ
    -0.15
    aju
    -0.15
    vert
    -0.15
    rank
    -0.14
    POSITIVE LOGITS
    lear
    0.15
    .dds
    0.15
    ãĤ´ãĥª
    0.14
    ilda
    0.14
    \DependencyInjection
    0.14
    boro
    0.14
    itant
    0.14
    ading
    0.14
     dio
    0.14
     Relative
    0.13
    Act Density 0.002%

    No Known Activations