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

    Neuronpedia

    INDEX
    Explanations

    words that have been given a specific name or title

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dubbed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    medi
    -0.69
    entity
    -0.65
     satisfaction
    -0.64
    ente
    -0.64
    âĨ
    -0.61
    ^^^^
    -0.60
     Satisf
    -0.60
     considerations
    -0.60
    *
    -0.58
     balance
    -0.58
    POSITIVE LOGITS
     dubbed
    3.62
     nicknamed
    2.56
     termed
    1.85
     dub
    1.54
     labelled
    1.53
     likened
    1.46
     titled
    1.45
     renamed
    1.45
     called
    1.39
     labeled
    1.38
    Act Density 0.019%

    No Known Activations