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

    Neuronpedia

    INDEX
    Explanations

    sports-related terms and player names

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports performance and player evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apologised
    -0.87
     apologise
    -0.81
     humour
    -0.70
     quotations
    -0.70
     recount
    -0.69
     inventions
    -0.67
    yrics
    -0.67
     provoked
    -0.66
     Franç
    -0.66
    è
    -0.66
    POSITIVE LOGITS
     versatility
    1.00
     matchup
    1.00
    Draft
    0.99
     backfield
    0.94
    nesota
    0.94
    Pred
    0.92
     scouts
    0.92
     underrated
    0.91
    Grade
    0.91
     upside
    0.90
    Act Density 0.687%

    No Known Activations