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

    Neuronpedia

    INDEX
    Explanations

    mentions or instances of providing or obtaining a copy of something

    oai_token-act-pair · gpt-3.5-turbo

    references to copies of documents or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igious
    -0.65
     horizont
    -0.64
    oji
    -0.63
     destro
    -0.63
     thirsty
    -0.63
     Vengeance
    -0.62
     Carnage
    -0.62
    itual
    -0.61
     Saga
    -0.61
     Fans
    -0.60
    POSITIVE LOGITS
     briefing
    0.94
     memo
    0.84
     excerpts
    0.84
     statement
    0.79
     memorandum
    0.78
    clinton
    0.78
    arling
    0.74
     wording
    0.74
     quotes
    0.74
     briefings
    0.74
    Act Density 0.194%

    No Known Activations