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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to historical figures or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and familial relationships in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Checking
    -0.82
    Loading
    -0.73
    Dispatch
    -0.73
    Review
    -0.72
    Tips
    -0.71
     Reporter
    -0.70
    Alright
    -0.69
    Check
    -0.69
    Async
    -0.69
    oking
    -0.69
    POSITIVE LOGITS
     died
    1.76
     perished
    1.72
     lived
    1.54
     resided
    1.50
     migrated
    1.43
     survived
    1.43
     sailed
    1.43
     married
    1.41
     fled
    1.36
     travelled
    1.35
    Act Density 0.316%

    No Known Activations