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

    Neuronpedia

    INDEX
    Explanations

    references to pardons and related actions or terms in the context of legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.03
    3:0.06
    4:0.12
    5:0.03
    6:0.02
    7:0.33
    8:0.02
    9:0.03
    10:0.17
    11:0.10
    Negative Logits
    ibaba
    -1.68
     Surviv
    -1.62
    yssey
    -1.61
     Construct
    -1.49
    mopolitan
    -1.46
     Beir
    -1.44
     sophistication
    -1.44
     Ratings
    -1.44
     Powered
    -1.43
     Generations
    -1.43
    POSITIVE LOGITS
     decree
    1.81
     pard
    1.76
     jailed
    1.75
     expired
    1.62
     indicted
    1.55
     convicted
    1.52
     punishable
    1.51
     ineligible
    1.51
     wrongdoing
    1.50
     pardon
    1.49
    Act Density 0.002%

    No Known Activations