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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "off."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ร
    -0.17
    uality
    -0.17
    à¸Ħ
    -0.16
    +offset
    -0.16
    -être
    -0.16
     offices
    -0.16
     Offensive
    -0.16
     offensive
    -0.15
    ohon
    -0.15
    aries
    -0.15
    POSITIVE LOGITS
    ensively
    0.42
    /on
    0.32
    site
    0.29
    beat
    0.29
    shoot
    0.28
    loaded
    0.24
    /down
    0.24
    -campus
    0.23
    screen
    0.23
    entimes
    0.23
    Act Density 0.064%

    No Known Activations