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

    Neuronpedia

    INDEX
    Explanations

    sentences ending in a period

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating official or authoritative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whilst
    -1.33
     Whilst
    -1.22
    Firstly
    -1.13
    ".[
    -1.04
    Contents
    -0.93
     Firstly
    -0.91
     ('
    -0.90
    ´
    -0.89
     afterwards
    -0.87
     recognise
    -0.86
    POSITIVE LOGITS
     layoffs
    1.00
     automakers
    0.95
     recession
    0.89
     nonprofits
    0.87
     slowdown
    0.86
     nonprofit
    0.84
     insurers
    0.83
     subsidies
    0.83
     pricey
    0.83
     DOE
    0.82
    Act Density 0.887%

    No Known Activations