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

    Neuronpedia

    INDEX
    Explanations

    Nobel Prizes and Pulitzer Prizes mentions in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to Nobel and Pulitzer Prizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.73
    bleacher
    -0.67
    avage
    -0.67
     Aber
    -0.66
     Antar
    -0.66
    aves
    -0.65
    akens
    -0.63
    amon
    -0.62
     Commodore
    -0.60
    ickr
    -0.59
    POSITIVE LOGITS
     Prize
    1.60
     laureate
    1.32
     laure
    1.16
    Pri
    1.12
     prize
    1.07
     Laure
    1.07
     Award
    0.91
     Pri
    0.90
     Peace
    0.88
     medal
    0.87
    Act Density 0.039%

    No Known Activations