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

    Neuronpedia

    INDEX
    Explanations

    words or roots related to the concept of light or brightness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.22
    t
    -0.21
    n
    -0.21
    re
    -0.20
    rer
    -0.20
    res
    -0.20
    reb
    -0.19
    d
    -0.19
    nat
    -0.19
    dust
    -0.18
    POSITIVE LOGITS
    ardy
    0.21
    brities
    0.21
    urope
    0.20
    aders
    0.19
    psy
    0.19
    phants
    0.18
    ighth
    0.18
    arning
    0.18
    opard
    0.18
    ADER
    0.17
    Act Density 0.123%

    No Known Activations