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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated references in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.13
    4:0.10
    5:0.03
    6:0.05
    7:0.32
    8:0.04
    9:0.04
    10:0.06
    11:0.08
    Negative Logits
    Lear
    -1.47
    Charges
    -1.43
    Bron
    -1.41
    Production
    -1.36
    WOOD
    -1.36
    bucks
    -1.36
    Companies
    -1.34
    SI
    -1.33
    SPONSORED
    -1.31
    Table
    -1.31
    POSITIVE LOGITS
     outcome
    1.68
     reconcil
    1.51
     authenticity
    1.39
    amac
    1.38
    abouts
    1.35
    anything
    1.33
     satisfactory
    1.32
     candid
    1.31
     pse
    1.30
     distingu
    1.30
    Act Density 0.006%

    No Known Activations