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

    Neuronpedia

    INDEX
    Explanations

    keywords related to searching, browsing, or going through content

    oai_token-act-pair · gpt-3.5-turbo

    activities related to scrolling and browsing through digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amen
    -0.88
    roit
    -0.84
    vantage
    -0.84
    ema
    -0.82
    ajor
    -0.75
     GOODMAN
    -0.73
    assador
    -0.71
    ENE
    -0.70
    kamp
    -0.70
    Support
    -0.70
    POSITIVE LOGITS
     folders
    1.34
     menus
    1.28
     piles
    1.23
     stacks
    1.22
     pages
    1.20
     notebooks
    1.18
     scraps
    1.13
     DVDs
    1.10
     paperwork
    1.10
     memos
    1.09
    Act Density 0.499%

    No Known Activations