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

    Neuronpedia

    INDEX
    Explanations

    keywords related to impeachment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.02
    2:0.26
    3:0.07
    4:0.03
    5:0.11
    6:0.04
    7:0.08
    8:0.12
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     agility
    -2.65
    �醒
    -2.60
     Rider
    -2.53
     Route
    -2.51
    natureconservancy
    -2.48
     Newtown
    -2.48
     hunter
    -2.44
     [|
    -2.44
    achine
    -2.43
     Surviv
    -2.41
    POSITIVE LOGITS
     impeachment
    7.51
     impe
    7.24
     perjury
    3.72
     Constitutional
    3.58
     Watergate
    3.56
     treason
    3.51
     indict
    3.47
     scandals
    3.44
     obstruction
    3.44
     defamation
    3.40
    Act Density 0.007%

    No Known Activations