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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "generate" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ram
    -0.17
    ñas
    -0.16
    strap
    -0.16
    ingles
    -0.15
    à¥įषण
    -0.15
    rol
    -0.14
    Ìģc
    -0.14
    unas
    -0.14
    ulse
    -0.14
    inge
    -0.14
    POSITIVE LOGITS
    ational
    0.27
    ative
    0.24
     Gener
    0.22
    ationally
    0.21
    osity
    0.20
    ations
    0.20
    icode
    0.19
     gener
    0.19
    ators
    0.19
    ality
    0.18
    Act Density 0.006%

    No Known Activations