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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data and trends over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.06
    2:0.04
    3:0.07
    4:0.05
    5:0.05
    6:0.21
    7:0.04
    8:0.04
    9:0.27
    10:0.02
    11:0.03
    Negative Logits
    elo
    -4.10
     Kom
    -3.83
     Bot
    -3.62
     Gol
    -3.54
     Pompe
    -3.49
    Mach
    -3.39
     Bolton
    -3.34
     Monsters
    -3.34
     Enchant
    -3.28
     Mach
    -3.27
    POSITIVE LOGITS
     quarter
    6.23
     quarters
    6.02
     Quarter
    5.81
    quarter
    5.55
    quarters
    4.54
     quarterly
    4.02
     sem
    3.91
    quad
    3.87
     Quinn
    3.77
    rums
    3.61
    Act Density 0.007%

    No Known Activations