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

    Neuronpedia

    INDEX
    Explanations

    the word "Ham."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Hamlet" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.66
     Kraken
    -0.64
     mushrooms
    -0.62
    UAL
    -0.60
     Veronica
    -0.59
     AVG
    -0.59
     electronically
    -0.58
     Staples
    -0.58
    âĶĢâĶĢ
    -0.57
     deforestation
    -0.57
    POSITIVE LOGITS
    mers
    1.42
    pton
    1.19
    elin
    1.18
    ster
    1.15
    monds
    1.14
    ilton
    1.13
    pered
    1.13
    ming
    1.12
    sters
    1.06
    pering
    1.05
    Act Density 0.011%

    No Known Activations