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

    Neuronpedia

    INDEX
    Explanations

    structured data related to authors, titles, and project statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “[
    -0.17
     (“
    -0.15
    ["_
    -0.15
    Ïīν
    -0.15
    ["@
    -0.15
     ("-
    -0.15
    ("#
    -0.14
    ("__
    -0.14
    \"\
    -0.14
    ("/
    -0.14
    POSITIVE LOGITS
     '
    0.54
    ='
    0.30
     ‘
    0.29
    '
    0.28
    ('
    0.25
    -'
    0.22
     '(
    0.22
    ,'
    0.21
    's
    0.21
     '"
    0.20
    Act Density 0.042%

    No Known Activations