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

    Neuronpedia

    INDEX
    Explanations

    expressions of regulatory obligations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.05
    2:0.01
    3:0.10
    4:0.03
    5:0.13
    6:0.04
    7:0.03
    8:0.28
    9:0.17
    10:0.01
    11:0.02
    Negative Logits
    ecd
    -2.03
     charisma
    -1.99
     fades
    -1.90
     glam
    -1.89
     speeches
    -1.87
     bubbles
    -1.84
     whispers
    -1.84
     reminiscent
    -1.80
     anecdotes
    -1.80
     intrigue
    -1.78
    POSITIVE LOGITS
     jurisdiction
    2.23
     plans
    1.97
     insurer
    1.96
     initiative
    1.94
    Plan
    1.91
     indemn
    1.85
     Revenue
    1.82
    venue
    1.80
    addons
    1.79
     funding
    1.79
    Act Density 0.051%

    No Known Activations