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

    Neuronpedia

    INDEX
    Explanations

    references to significant financial documents or budget proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.12
    3:0.12
    4:0.06
    5:0.05
    6:0.07
    7:0.05
    8:0.08
    9:0.07
    10:0.14
    11:0.11
    Negative Logits
    osate
    -1.44
     Azerb
    -1.41
     Bord
    -1.35
     Ferry
    -1.29
    abwe
    -1.29
    apon
    -1.27
     Rosenberg
    -1.25
     Pric
    -1.25
    negie
    -1.24
    kefeller
    -1.23
    POSITIVE LOGITS
    iframe
    1.54
    Title
    1.45
    clude
    1.29
    Hide
    1.27
    aved
    1.27
    etc
    1.27
    endars
    1.27
    Prev
    1.25
    Runtime
    1.25
    []
    1.25
    Act Density 0.000%

    No Known Activations