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

    Neuronpedia

    INDEX
    Explanations

    images and descriptions of visual art

    oai_token-act-pair · gpt-3.5-turbo

    instances of visual content or images within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erous
    -0.71
    ebus
    -0.70
    inqu
    -0.68
    eteria
    -0.68
    verning
    -0.68
     Regulations
    -0.65
    quire
    -0.64
     clauses
    -0.64
     Limits
    -0.63
    iola
    -0.63
    POSITIVE LOGITS
     depicting
    1.39
     cropped
    1.31
     depicts
    1.31
     depict
    1.28
     caption
    1.25
     blurry
    1.19
     illustrating
    1.17
     showing
    1.16
    phot
    1.14
     reproduced
    1.13
    Act Density 0.389%

    No Known Activations