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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to legal and administrative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.03
    3:0.05
    4:0.03
    5:0.03
    6:0.11
    7:0.02
    8:0.03
    9:0.56
    10:0.02
    11:0.01
    Negative Logits
     Elise
    -3.27
     onion
    -3.02
     reptiles
    -2.96
    �
    -2.96
    ince
    -2.88
    entin
    -2.85
     emot
    -2.83
    Mem
    -2.81
    emort
    -2.75
    ussen
    -2.71
    POSITIVE LOGITS
    b
    5.62
    B
    5.51
     BI
    5.48
    BB
    5.45
    bb
    5.39
    bm
    5.33
     Bib
    5.22
    BA
    5.21
    IB
    5.17
    bah
    5.04
    Act Density 0.382%

    No Known Activations