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

    Neuronpedia

    INDEX
    Explanations

    words related to prestigious awards or recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to various prestigious awards, particularly prizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mixed
    -0.70
     toe
    -0.68
    ted
    -0.65
     inconsistent
    -0.65
     sing
    -0.64
     skelet
    -0.63
    amac
    -0.62
     snap
    -0.62
     ammon
    -0.62
     mesh
    -0.62
    POSITIVE LOGITS
     Prize
    3.91
     prize
    2.14
     prizes
    1.73
    Pri
    1.66
     Award
    1.64
     Pri
    1.34
     Nobel
    1.33
     laureate
    1.29
     Medal
    1.29
     Contest
    1.26
    Act Density 0.013%

    No Known Activations