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

    Neuronpedia

    INDEX
    Explanations

    words that convey rapid actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dek
    -0.17
     finally
    -0.16
    mts
    -0.15
    bett
    -0.15
     continued
    -0.14
    ako
    -0.14
    herits
    -0.14
    VERBOSE
    -0.14
    iego
    -0.14
    наÑĤ
    -0.14
    POSITIVE LOGITS
     soon
    0.20
     Soon
    0.18
     chóng
    0.17
    Soon
    0.17
    ano
    0.17
    soon
    0.16
    ovan
    0.16
     quickly
    0.16
    zeitig
    0.15
    erc
    0.15
    Act Density 0.061%

    No Known Activations