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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "write" and its variations, emphasizing the act of writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ade
    -0.18
    h
    -0.17
    x
    -0.16
    WEEN
    -0.15
    asio
    -0.15
    yg
    -0.15
     Wagner
    -0.15
    /goto
    -0.15
    vir
    -0.14
    w
    -0.14
    POSITIVE LOGITS
    tatus
    0.18
    /photo
    0.16
    oire
    0.16
     tắt
    0.16
    ValueCollection
    0.15
    inus
    0.15
    noinspection
    0.15
    еÑģа
    0.15
    unsch
    0.14
    üns
    0.14
    Act Density 0.102%

    No Known Activations