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

    Neuronpedia

    INDEX
    Explanations

    economic and social terms related to governmental policies and situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to food-related taxation and economic policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.02
    2:0.19
    3:0.06
    4:0.17
    5:0.11
    6:0.03
    7:0.03
    8:0.08
    9:0.10
    10:0.06
    11:0.03
    Negative Logits
    yip
    -1.59
    ernels
    -1.30
     heed
    -1.30
     underest
    -1.29
    ront
    -1.26
    occup
    -1.25
    ebus
    -1.22
    imeo
    -1.21
    elight
    -1.21
    ishers
    -1.20
    POSITIVE LOGITS
     Poe
    1.30
     Haf
    1.28
     PD
    1.25
     Torn
    1.25
     Mu
    1.23
     Carnage
    1.23
     Wer
    1.21
     MED
    1.20
     Collection
    1.18
    Sad
    1.18
    Act Density 0.002%

    No Known Activations