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

    Neuronpedia

    INDEX
    Explanations

    references to "light" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -1.25
    __":
    -1.13
     "..\..\..\
    -1.11
    AndEndTag
    -1.05
     Anfitrión
    -1.04
    ngdoc
    -1.01
    URLException
    -0.99
     للاسماء
    -0.99
    ganu
    -0.99
     pitié
    -0.99
    POSITIVE LOGITS
     Light
    1.98
    Light
    1.91
    light
    1.90
     light
    1.89
     LIGHT
    1.84
    LIGHT
    1.68
     licht
    1.21
    lights
    1.19
     ligh
    1.18
     Licht
    1.18
    Act Density 0.063%

    No Known Activations