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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.03
    3:0.06
    4:0.03
    5:0.04
    6:0.34
    7:0.10
    8:0.05
    9:0.05
    10:0.09
    11:0.09
    Negative Logits
    ottesville
    -1.32
    istration
    -1.29
    BuyableInstoreAndOnline
    -1.29
     Aval
    -1.28
    Generic
    -1.26
     ensu
    -1.24
    )=(
    -1.23
    HAHAHAHA
    -1.20
    BIL
    -1.18
    Gh
    -1.15
    POSITIVE LOGITS
    opolis
    1.45
    arta
    1.43
    ews
    1.20
    atoon
    1.18
    ocket
    1.17
    woods
    1.14
    ointed
    1.10
     Rein
    1.09
    ropolitan
    1.09
     Ends
    1.08
    Act Density 0.001%

    No Known Activations