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

    Neuronpedia

    INDEX
    Explanations

    photography credits in captions

    oai_token-act-pair · gpt-3.5-turbo

    references to images and photo credits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.73
    cible
    -0.71
    nesia
    -0.67
    yip
    -0.66
     debilitating
    -0.66
    floor
    -0.66
    etheless
    -0.62
     unsus
    -0.61
     tranquil
    -0.60
     corros
    -0.60
    POSITIVE LOGITS
     Images
    0.98
     Entertainment
    0.97
     IMAGES
    0.81
     Ltd
    0.79
     Features
    0.78
     Agency
    0.77
    Library
    0.74
     Universe
    0.73
    File
    0.73
     Library
    0.73
    Act Density 0.030%

    No Known Activations