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

    Neuronpedia

    INDEX
    Explanations

    numeric statistics related to player performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urat
    -0.16
    ammers
    -0.15
    agini
    -0.15
    arget
    -0.15
    ì½
    -0.15
    otte
    -0.14
    adio
    -0.14
    makta
    -0.14
    tube
    -0.14
    eatures
    -0.14
    POSITIVE LOGITS
     steals
    0.30
     assist
    0.29
     assists
    0.29
     blocks
    0.26
     steal
    0.25
    Blocks
    0.23
     Ste
    0.23
     Blocks
    0.23
     Assist
    0.23
     rebounds
    0.23
    Act Density 0.032%

    No Known Activations