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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the name "Ann."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     questioning
    -0.65
     sting
    -0.62
     td
    -0.62
     Scouting
    -0.61
    ======
    -0.60
     passage
    -0.59
     logger
    -0.59
     Combine
    -0.58
     mistaken
    -0.58
    vous
    -0.57
    POSITIVE LOGITS
    ouncing
    1.50
    ihilation
    1.49
    ihil
    1.44
    ounced
    1.43
    ounces
    1.40
    apolis
    1.38
    unciation
    1.37
    ounce
    1.32
    abel
    1.29
    iversary
    1.29
    Act Density 0.016%

    No Known Activations