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

    Neuronpedia

    INDEX
    Explanations

    key terms related to themes of power, governance, and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.04
    3:0.05
    4:0.05
    5:0.34
    6:0.02
    7:0.04
    8:0.02
    9:0.26
    10:0.02
    11:0.05
    Negative Logits
     tended
    -2.82
     tend
    -2.69
    suggest
    -2.63
    り
    -2.62
    glers
    -2.58
    uggest
    -2.53
     partName
    -2.48
    Interstitial
    -2.48
     guiActiveUnfocused
    -2.46
     caution
    -2.46
    POSITIVE LOGITS
     forever
    4.22
     radically
    2.63
    onential
    2.53
     decades
    2.52
     democratically
    2.50
     humankind
    2.50
    thood
    2.48
    ament
    2.48
    clusively
    2.47
    itutional
    2.47
    Act Density 0.303%

    No Known Activations