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

    Neuronpedia

    INDEX
    Explanations

    occurrences of financial terms and contract-related language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.00
    2:0.09
    3:0.04
    4:0.08
    5:0.03
    6:0.04
    7:0.41
    8:0.02
    9:0.05
    10:0.13
    11:0.06
    Negative Logits
     weighs
    -1.56
    capacity
    -1.43
    notice
    -1.35
    FontSize
    -1.34
    ��極
    -1.32
     understatement
    -1.31
    00007
    -1.26
    iewicz
    -1.25
     NOTICE
    -1.25
    ovsky
    -1.23
    POSITIVE LOGITS
    adesh
    1.74
     various
    1.62
    arent
    1.57
    everal
    1.56
    lict
    1.51
    airs
    1.47
    alach
    1.41
    aults
    1.38
    avorite
    1.37
     sites
    1.36
    Act Density 0.900%

    No Known Activations