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

    Neuronpedia

    INDEX
    Explanations

    mentions of various types of light or descriptors related to light

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -1.06
    原始内容存档于
    -0.99
    __":
    -0.98
     Anfitrión
    -0.96
     propOrder
    -0.95
    ngdoc
    -0.92
     "..\..\
    -0.92
     Escobar
    -0.92
    ganu
    -0.91
     logique
    -0.90
    POSITIVE LOGITS
     Light
    2.28
     light
    2.26
    Light
    2.20
    light
    2.18
     LIGHT
    2.13
    LIGHT
    1.92
     licht
    1.42
    lights
    1.42
     ligh
    1.38
     Licht
    1.37
    Act Density 0.045%

    No Known Activations