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

    Neuronpedia

    INDEX
    Explanations

    mentions of the Olympics

    oai_token-act-pair · gpt-3.5-turbo

    references to the Olympics and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atter
    -0.66
    ellar
    -0.63
    iffs
    -0.63
    ane
    -0.62
    ESH
    -0.62
    IVER
    -0.61
     chang
    -0.60
     possess
    -0.60
    iver
    -0.60
     spectral
    -0.59
    POSITIVE LOGITS
     Olympics
    3.65
     Olympic
    2.16
     Olymp
    1.72
     Paraly
    1.58
     Sochi
    1.52
     IOC
    1.48
     Oscars
    1.46
    lymp
    1.39
     Games
    1.28
     Rio
    1.10
    Act Density 0.012%

    No Known Activations