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

    Neuronpedia

    INDEX
    Explanations

    keywords related to shadows, lighting, and photography techniques

    oai_token-act-pair · gpt-3.5-turbo

    references to shadows in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keye
    -0.94
    entric
    -0.86
    urses
    -0.81
    TAIN
    -0.76
    keyes
    -0.73
    OY
    -0.73
    awaru
    -0.73
    olics
    -0.71
    ĵĺ
    -0.69
    renheit
    -0.69
    POSITIVE LOGITS
    loo
    0.89
    bite
    0.88
     Shadows
    0.84
    hawk
    0.84
    moon
    0.83
     Shadow
    0.81
    mere
    0.78
    Shadow
    0.77
    bolt
    0.77
    overs
    0.76
    Act Density 0.011%

    No Known Activations