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

    Neuronpedia

    INDEX
    Explanations

    mentions or references to archives

    oai_token-act-pair · gpt-3.5-turbo

    words related to archival content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nir
    -0.86
    osuke
    -0.81
    stad
    -0.75
    ggle
    -0.73
    hood
    -0.72
    alties
    -0.72
    yah
    -0.68
    lied
    -0.68
    ners
    -0.66
    nen
    -0.66
    POSITIVE LOGITS
     trove
    0.95
     archives
    0.91
     archive
    0.89
     Archive
    0.85
    archives
    0.84
     dumps
    0.81
     documenting
    0.79
     Archives
    0.79
    ngth
    0.78
     collection
    0.78
    Act Density 0.034%

    No Known Activations