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

    Neuronpedia

    INDEX
    Explanations

    mentions of "light" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oky
    -0.18
    aggi
    -0.15
    iente
    -0.15
    ivre
    -0.15
    .ColumnHeader
    -0.14
    oltip
    -0.14
    ppers
    -0.14
    ifr
    -0.14
    件
    -0.14
    rss
    -0.14
    POSITIVE LOGITS
    ened
    0.22
    bul
    0.19
    nings
    0.18
    ening
    0.18
    enment
    0.18
    fully
    0.17
    undef
    0.16
    ning
    0.15
    fold
    0.15
    weights
    0.14
    Act Density 0.067%

    No Known Activations