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

    Neuronpedia

    INDEX
    Explanations

    revised versions of various items or documents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "revised" and "upgraded."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abal
    -0.70
    ake
    -0.66
    ggle
    -0.62
    igent
    -0.62
    istence
    -0.62
     proble
    -0.61
    anyl
    -0.61
    WAR
    -0.61
     itch
    -0.60
    ache
    -0.59
    POSITIVE LOGITS
     revised
    2.40
     revamped
    2.20
     modified
    2.08
     expanded
    2.05
     upgraded
    2.03
     redesigned
    1.97
     tweaked
    1.96
     shortened
    1.91
     updated
    1.90
     amended
    1.81
    Act Density 0.049%

    No Known Activations