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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legislation and legal authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.08
    2:0.04
    3:0.04
    4:0.04
    5:0.03
    6:0.04
    7:0.48
    8:0.04
    9:0.05
    10:0.03
    11:0.03
    Negative Logits
    oké
    -3.15
    haar
    -3.15
    enberg
    -2.86
    gow
    -2.73
    iop
    -2.63
    earch
    -2.63
    oris
    -2.55
    abis
    -2.51
    elman
    -2.50
    raq
    -2.45
    POSITIVE LOGITS
     fourth
    3.54
    Fourth
    3.47
    fourth
    2.72
    INE
    2.71
     [&
    2.69
    second
    2.58
     Fourth
    2.52
     Single
    2.49
     First
    2.47
     Second
    2.45
    Act Density 0.041%

    No Known Activations