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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns, particularly "your" and "our."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.12
    3:0.05
    4:0.11
    5:0.07
    6:0.07
    7:0.12
    8:0.08
    9:0.07
    10:0.13
    11:0.11
    Negative Logits
    vernment
    -1.47
    inventoryQuantity
    -1.45
    nces
    -1.45
    matical
    -1.44
     Rodham
    -1.43
    jri
    -1.42
    ntil
    -1.40
     behaves
    -1.40
    hift
    -1.40
    rition
    -1.38
    POSITIVE LOGITS
    NBA
    1.47
     subconscious
    1.36
     Starcraft
    1.33
    POST
    1.33
    Lens
    1.32
     periphery
    1.32
     shelves
    1.31
     iTunes
    1.31
    CSS
    1.28
     UEFA
    1.23
    Act Density 0.068%

    No Known Activations