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

    Neuronpedia

    INDEX
    Explanations

    pictures or images within text

    oai_token-act-pair · gpt-3.5-turbo

    references to images and photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.86
    ensable
    -0.76
     Revel
    -0.74
    ruciating
    -0.73
    osponsors
    -0.71
    aughs
    -0.70
    ENDED
    -0.69
    iott
    -0.68
    development
    -0.67
    ses
    -0.67
    POSITIVE LOGITS
     depicting
    0.99
     caption
    0.90
     photograph
    0.89
     photo
    0.83
     photographed
    0.82
     thereof
    0.82
     image
    0.81
     picture
    0.79
     portrait
    0.79
    journal
    0.79
    Act Density 0.085%

    No Known Activations