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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and structures within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.14
    1:0.03
    2:0.00
    3:0.12
    4:0.30
    5:0.07
    6:0.03
    7:0.02
    8:0.13
    9:0.07
    10:0.01
    11:0.01
    Negative Logits
    PLA
    -2.38
    ription
    -2.11
    DERR
    -2.07
    kish
    -2.00
    untled
    -1.96
    mails
    -1.96
    undreds
    -1.94
    omever
    -1.93
    ullivan
    -1.90
    anto
    -1.88
    POSITIVE LOGITS
    2.48
     constituted
    2.27
     ⓘ
    2.13
     1967
    2.01
     constitutes
    1.99
     1937
    1.97
    =(
    1.93
     Catalyst
    1.92
     plunged
    1.91
     1947
    1.91
    Act Density 0.015%

    No Known Activations