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

    Neuronpedia

    INDEX
    Explanations

    references to pubs

    oai_token-act-pair · gpt-3.5-turbo

    references to pubs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketable
    -0.83
    ioxide
    -0.78
     GOODMAN
    -0.74
     Gaia
    -0.74
    llor
    -0.67
     Fey
    -0.64
     EFF
    -0.64
    points
    -0.63
     Grace
    -0.63
    CVE
    -0.62
    POSITIVE LOGITS
    lique
    1.18
    escent
    1.11
    lishes
    1.04
    lish
    1.01
     crawl
    0.88
    cers
    0.87
    bing
    0.85
    elling
    0.85
    ishes
    0.84
    lik
    0.83
    Act Density 0.006%

    No Known Activations