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

    Neuronpedia

    INDEX
    Explanations

    references to legal or judicial topics, specifically concerning obstruction of justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.04
    3:0.05
    4:0.10
    5:0.02
    6:0.21
    7:0.28
    8:0.03
    9:0.03
    10:0.12
    11:0.05
    Negative Logits
     Units
    -1.56
    sterdam
    -1.54
    ourge
    -1.54
     sexes
    -1.52
    版
    -1.52
    odium
    -1.51
    onomous
    -1.47
     Glob
    -1.44
     genders
    -1.43
    adult
    -1.43
    POSITIVE LOGITS
     smear
    1.91
     perjury
    1.66
     omission
    1.62
     obstruction
    1.52
     prosecution
    1.47
     detract
    1.44
     Prosecut
    1.43
     disclosure
    1.41
     divul
    1.41
     obfusc
    1.41
    Act Density 0.000%

    No Known Activations