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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "light" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieren
    -0.16
    "struct
    -0.15
     Chap
    -0.15
    Ĺı
    -0.15
    umpt
    -0.15
    ptime
    -0.14
    adr
    -0.14
    ÑĨвеÑĤ
    -0.14
    insky
    -0.14
     stare
    -0.14
    POSITIVE LOGITS
    ening
    0.15
    uto
    0.14
    nings
    0.14
    ened
    0.14
    аÑĤков
    0.14
    æĪIJ人
    0.14
    UTO
    0.14
     halo
    0.13
     autumn
    0.13
    gravity
    0.13
    Act Density 0.019%

    No Known Activations