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

    Neuronpedia

    INDEX
    Explanations

    terms related to functionality and operational features, particularly those dealing with automatic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.28
    1:0.05
    2:0.01
    3:0.06
    4:0.06
    5:0.08
    6:0.05
    7:0.02
    8:0.24
    9:0.06
    10:0.02
    11:0.02
    Negative Logits
     bruised
    -1.89
     traveller
    -1.71
    BuyableInstoreAndOnline
    -1.70
     diam
    -1.61
     stranger
    -1.53
     Lauder
    -1.52
     Boyle
    -1.48
     trove
    -1.48
     hostages
    -1.47
     Qiao
    -1.43
    POSITIVE LOGITS
    omatic
    1.85
     Sync
    1.80
     autop
    1.75
     automate
    1.74
    �
    1.74
    creen
    1.74
    activation
    1.72
     sync
    1.71
     automation
    1.70
    tool
    1.69
    Act Density 0.001%

    No Known Activations