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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "row"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.08
    11:0.09
    Negative Logits
    wolves
    -2.56
    gress
    -2.22
    ults
    -2.13
    eus
    -2.13
    danger
    -2.13
    ocalypse
    -2.10
    ↵ 
    -2.09
     Learned
    -2.06
    cest
    -2.04
    alys
    -2.01
    POSITIVE LOGITS
     garment
    2.69
     contractor
    2.27
     arrangement
    2.21
     vessel
    2.08
     booklet
    2.07
     garments
    2.04
     1967
    2.01
    Buyable
    2.00
    TRUMP
    1.98
     Jindal
    1.97
    Act Density 0.000%

    No Known Activations