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

    Neuronpedia

    INDEX
    Explanations

    references to sports teams and their performance statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´
    -0.89
    speech
    -0.83
    ortment
    -0.80
    ãĥł
    -0.77
     readings
    -0.76
     horm
    -0.71
     exper
    -0.70
     reversible
    -0.70
    anasia
    -0.70
     modesty
    -0.69
    POSITIVE LOGITS
     Royals
    1.33
     Tigers
    1.30
     Mariners
    1.29
     Bulldogs
    1.26
     Colts
    1.25
     Chiefs
    1.25
     Yankees
    1.21
     Dodgers
    1.20
     Packers
    1.19
     Bengals
    1.17
    Act Density 0.100%

    No Known Activations