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

    Neuronpedia

    INDEX
    Explanations

    pictures or photos

    oai_token-act-pair · gpt-3.5-turbo

    references to photos or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.92
    ãĤ¦ãĤ¹
    -0.85
     levied
    -0.76
     rely
    -0.74
     depended
    -0.74
     relies
    -0.72
     partName
    -0.70
     relied
    -0.70
     strengthens
    -0.68
    wcs
    -0.67
    POSITIVE LOGITS
    tnc
    0.86
     smiling
    0.82
     naked
    0.81
     flowers
    0.78
     kittens
    0.77
     him
    0.77
     lifeless
    0.75
     genitals
    0.72
     silhou
    0.72
     celebrities
    0.71
    Act Density 0.139%

    No Known Activations