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

    Neuronpedia

    INDEX
    Explanations

    references to player statistics and performance in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.08
    4:0.17
    5:0.03
    6:0.03
    7:0.16
    8:0.05
    9:0.04
    10:0.11
    11:0.12
    Negative Logits
     Calories
    -1.45
     References
    -1.34
    actionDate
    -1.25
    NetMessage
    -1.20
     Adren
    -1.20
     clocks
    -1.19
    orses
    -1.19
    aptic
    -1.19
    ument
    -1.17
    zyme
    -1.17
    POSITIVE LOGITS
     burg
    1.35
     Kik
    1.32
     DPR
    1.28
     abroad
    1.21
    ヴァ
    1.21
     intermitt
    1.20
     unprotected
    1.18
     Uk
    1.17
     havoc
    1.15
     advoc
    1.13
    Act Density 0.001%

    No Known Activations