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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing dissatisfaction or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    instances of words related to the concept of meaning or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.72
     Compass
    -0.67
    lines
    -0.64
    liners
    -0.64
    ython
    -0.63
     Rabbit
    -0.60
     Pixie
    -0.60
     Anthropology
    -0.59
    rag
    -0.58
    enegger
    -0.58
    POSITIVE LOGITS
    ctions
    1.05
    fters
    1.04
    pered
    1.03
    fter
    1.02
    vers
    0.99
    ction
    0.99
    isance
    0.98
    uthor
    0.98
    vered
    0.97
    BILITY
    0.97
    Act Density 0.109%

    No Known Activations