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

    Neuronpedia

    INDEX
    Explanations

    high-quality visual attributes in images and their effects on clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¨Ģ
    -0.15
     Hunger
    -0.14
    _decorator
    -0.14
    132
    -0.14
    åł±
    -0.14
    alar
    -0.13
     sniff
    -0.13
     fragrance
    -0.13
    ahn
    -0.13
    anz
    -0.13
    POSITIVE LOGITS
     detail
    0.24
    /detail
    0.23
     artifacts
    0.22
     artifact
    0.22
     Detail
    0.22
    detail
    0.22
     saturation
    0.22
     punch
    0.21
     saturated
    0.21
     arte
    0.20
    Act Density 0.030%

    No Known Activations