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

    Neuronpedia

    INDEX
    Explanations

    individual names, specifically in a sporting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.07
    7:0.07
    8:0.07
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     Flesh
    -3.55
     Log
    -3.20
     Retail
    -3.05
     Eater
    -2.94
     Liqu
    -2.93
     Spirits
    -2.91
     LOT
    -2.87
     Liv
    -2.83
     Warehouse
    -2.82
     Streaming
    -2.81
    POSITIVE LOGITS
    achev
    3.17
    advant
    3.09
     submer
    3.09
     guru
    3.01
     carbohyd
    2.99
    dinand
    2.96
    awar
    2.90
     meltdown
    2.88
    arthed
    2.83
    ichick
    2.80
    Act Density 0.000%

    No Known Activations