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

    Neuronpedia

    INDEX
    Explanations

    abstract or technical terms and specialized vocabulary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.35
    4:0.02
    5:0.02
    6:0.05
    7:0.13
    8:0.05
    9:0.06
    10:0.08
    11:0.09
    Negative Logits
    rities
    -1.27
    ufact
    -1.19
    rences
    -1.13
    stocks
    -1.10
    letter
    -1.09
    child
    -1.08
    �
    -1.08
    bart
    -1.05
    anne
    -1.03
    advertising
    -1.01
    POSITIVE LOGITS
    ippi
    1.48
    vous
    1.32
    emia
    1.18
    pter
    1.12
    ldon
    1.03
    agog
    1.03
     indo
    1.03
    OSH
    1.00
     glutamate
    0.99
    rha
    0.97
    Act Density 0.003%

    No Known Activations