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

    Neuronpedia

    INDEX
    Explanations

    files or messages hidden within text

    oai_token-act-pair · gpt-3.5-turbo

    references to images in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hurst
    -0.92
    cffff
    -0.78
    aptic
    -0.76
    doms
    -0.76
    iability
    -0.75
    dule
    -0.75
    woods
    -0.73
    uckle
    -0.72
    anus
    -0.72
    itte
    -0.70
    POSITIVE LOGITS
     gallery
    1.11
     galleries
    1.04
     caption
    1.04
    gallery
    1.01
     depicting
    0.93
     img
    0.90
     Gallery
    0.86
    Capture
    0.86
    upload
    0.86
    scape
    0.85
    Act Density 0.050%

    No Known Activations