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

    Neuronpedia

    INDEX
    Explanations

    specific actions or processes that involve the creation or generation of something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the production or creation of items, ideas, or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.11
    3:0.09
    4:0.03
    5:0.09
    6:0.03
    7:0.02
    8:0.30
    9:0.11
    10:0.05
    11:0.02
    Negative Logits
    Developer
    -1.32
    Args
    -1.17
    uyomi
    -1.17
     Brist
    -1.15
    Controller
    -1.15
    Owner
    -1.12
     Cursed
    -1.11
     Seas
    -1.10
     Owner
    -1.10
    itsch
    -1.09
    POSITIVE LOGITS
    aganda
    1.50
    DragonMagazine
    1.38
    artifacts
    1.38
    TEXTURE
    1.28
     quantities
    1.22
    minus
    1.20
     transcripts
    1.20
    actory
    1.16
     Flavoring
    1.15
     batches
    1.14
    Act Density 0.079%

    No Known Activations