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

    Neuronpedia

    INDEX
    Explanations

    different types of plays in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "play"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    «ĺ
    -0.69
     Unic
    -0.68
    orpor
    -0.67
     mosqu
    -0.67
     temporal
    -0.66
     unden
    -0.65
    ++++++++++++++++
    -0.64
     Apost
    -0.64
     Imperium
    -0.62
    izoph
    -0.62
    POSITIVE LOGITS
    wright
    1.25
    ername
    1.19
    maker
    1.17
    makers
    1.05
    plays
    1.03
    wr
    0.99
    offs
    0.96
    writing
    0.95
    books
    0.94
    fulness
    0.94
    Act Density 0.035%

    No Known Activations