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

    Neuronpedia

    INDEX
    Explanations

    multi-digit numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20
    -0.67
    SPONSORED
    -0.62
    min
    -0.59
    Wall
    -0.59
    Acknowled
    -0.57
    21
    -0.57
    00
    -0.56
    Pred
    -0.55
    FactoryReloaded
    -0.55
    tier
    -0.55
    POSITIVE LOGITS
     323
    2.17
     337
    2.16
     321
    2.15
     353
    2.14
     354
    2.13
     376
    2.13
     322
    2.12
     373
    2.12
     335
    2.11
     344
    2.10
    Act Density 0.048%

    No Known Activations