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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names, particularly those related to announcements or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ann."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scouting
    -0.67
    EStreamFrame
    -0.67
     questioning
    -0.66
    vous
    -0.64
     logger
    -0.62
     dstg
    -0.60
    llan
    -0.59
     conduct
    -0.59
     ants
    -0.58
     sanitation
    -0.58
    POSITIVE LOGITS
    ihilation
    1.53
    ihil
    1.52
    ouncing
    1.44
    iversary
    1.42
    ounces
    1.40
    ounced
    1.38
    unciation
    1.37
    apolis
    1.29
    abeth
    1.28
    ounce
    1.27
    Act Density 0.024%

    No Known Activations