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

    Neuronpedia

    INDEX
    Explanations

    specific terms and names, particularly related to semiconductor technology and associated measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    short, lowercase subword fragments—often two-letter sequences—and common snake_case prefixes in code/technical contexts.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
    й
    -1.10
    一个
    -0.92
    йки
    -0.87
     Sapi
    -0.83
     Bartol
    -0.82
    kém
    -0.81
     manufact
    -0.81
     Baldwin
    -0.77
    Gott
    -0.77
     dale
    -0.77
    POSITIVE LOGITS
     Lynd
    0.89
     soeur
    0.89
     nationaux
    0.85
     sabbia
    0.84
    ly
    0.84
     suivie
    0.84
    に
    0.82
     Landis
    0.78
     Rha
    0.77
    hoeddwyd
    0.76
    Act Density 1.398%

    No Known Activations