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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to social and economic issues, particularly addressing government accountability and social justice concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.13
    3:0.08
    4:0.42
    5:0.03
    6:0.04
    7:0.07
    8:0.03
    9:0.04
    10:0.04
    11:0.05
    Negative Logits
    EStream
    -1.79
    rontal
    -1.76
    BILITIES
    -1.75
    aughtered
    -1.68
    blem
    -1.66
    hemy
    -1.65
    ivable
    -1.63
    rection
    -1.58
    ilic
    -1.57
    QB
    -1.55
    POSITIVE LOGITS
     dear
    1.89
     volunteers
    1.63
     sorely
    1.53
    cells
    1.50
     comrade
    1.46
     Yorkers
    1.43
    alin
    1.42
     wield
    1.40
     travellers
    1.39
     dearly
    1.37
    Act Density 0.193%

    No Known Activations