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

    Neuronpedia

    INDEX
    Explanations

    specific technical jargon related to scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĭ¤ëĬĶ
    -0.17
    çłģ
    -0.16
    forman
    -0.15
    ivate
    -0.15
    ions
    -0.15
    inition
    -0.15
    ÑĪи
    -0.15
    flater
    -0.14
    imately
    -0.14
    jspx
    -0.14
    POSITIVE LOGITS
    er
    0.65
    e
    0.57
    a
    0.55
    y
    0.52
    o
    0.50
    i
    0.45
    ÙĬ
    0.39
    ÛĮ
    0.38
    an
    0.36
    ing
    0.33
    Act Density 1.877%

    No Known Activations