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

    Neuronpedia

    INDEX
    Explanations

    phrases or numbers related to financial values and monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.03
    3:0.11
    4:0.04
    5:0.11
    6:0.06
    7:0.10
    8:0.02
    9:0.09
    10:0.03
    11:0.28
    Negative Logits
    [/
    -3.67
    ``
    -3.62
    _>
    -3.39
    !:
    -3.33
    \)
    -3.24
    :\
    -3.18
    =[
    -3.11
    @@
    -3.04
    :'
    -2.97
    .}
    -2.90
    POSITIVE LOGITS
     tum
    2.52
     1
    2.48
     crem
    2.47
    osate
    2.45
    usra
    2.41
     burial
    2.36
     6
    2.32
     trance
    2.31
     2
    2.30
     calib
    2.28
    Act Density 0.002%

    No Known Activations