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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.18
    ander
    -0.16
    ewe
    -0.15
    idon
    -0.14
    oders
    -0.14
    kv
    -0.14
    owns
    -0.14
    SD
    -0.14
    fte
    -0.14
    sus
    -0.14
    POSITIVE LOGITS
     is
    0.15
     includes
    0.15
    окÑģи
    0.15
    Ïģιά
    0.15
    748
    0.15
    Queryable
    0.14
     itself
    0.14
    ambient
    0.14
     Dock
    0.14
    ilig
    0.14
    Act Density 0.094%

    No Known Activations