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

    Neuronpedia

    INDEX
    Explanations

    elements related to shadows and lighting effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owl
    -0.18
    bai
    -0.17
    yte
    -0.16
    bsub
    -0.15
    adel
    -0.14
    ving
    -0.14
    URRED
    -0.14
    _REGISTRY
    -0.14
    gil
    -0.14
     Gow
    -0.14
    POSITIVE LOGITS
     shadows
    0.30
     shadow
    0.27
    _shadow
    0.24
     Shadow
    0.23
     Shadows
    0.22
    .shadow
    0.22
    shadow
    0.22
    Shadow
    0.20
     projected
    0.19
    -shadow
    0.18
    Act Density 0.056%

    No Known Activations