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

    Neuronpedia

    INDEX
    Explanations

    references to Nobel Prize winners and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rating
    -0.20
     Ratings
    -0.18
    opian
    -0.17
     rating
    -0.16
    orgia
    -0.15
    -rating
    -0.15
     Kho
    -0.15
    éijij
    -0.14
    '=>['
    -0.14
    yro
    -0.14
    POSITIVE LOGITS
     Nobel
    0.43
     nob
    0.34
     Nob
    0.33
    nob
    0.28
     Noble
    0.28
     laure
    0.25
     awarded
    0.25
     Laure
    0.23
     Fields
    0.23
     prize
    0.21
    Act Density 0.019%

    No Known Activations