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

    Neuronpedia

    INDEX
    Explanations

    mentions of Nobel Prizes and related terms, such as laureates and winners

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Nobel Prizes and laureates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aber
    -0.73
    src
    -0.73
    mson
    -0.70
     Sega
    -0.70
    HUD
    -0.65
    anwhile
    -0.64
    alter
    -0.62
    rome
    -0.62
    okemon
    -0.61
     Antar
    -0.61
    POSITIVE LOGITS
     Prize
    1.72
     laureate
    1.58
     laure
    1.30
     Laure
    1.22
    Pri
    1.19
     prize
    1.16
    Nob
    1.08
     Award
    1.04
     pri
    0.99
     Pri
    0.97
    Act Density 0.037%

    No Known Activations