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

    Neuronpedia

    INDEX
    Explanations

    elements related to light and darkness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.15
     Gef
    -0.14
    .Mutable
    -0.14
    iser
    -0.14
    çĤī
    -0.14
     Lazar
    -0.13
     libre
    -0.13
    emouth
    -0.13
    Resizable
    -0.13
    è¨Ģãģ£ãģŁ
    -0.13
    POSITIVE LOGITS
     darkness
    0.30
     night
    0.28
     light
    0.28
     dark
    0.27
    -dark
    0.24
    dark
    0.24
     dim
    0.24
    light
    0.24
    -light
    0.23
    .dark
    0.23
    Act Density 0.102%

    No Known Activations