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

    Neuronpedia

    INDEX
    Explanations

    mentions of people and specific events in news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals along with their actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonprofits
    -0.70
    ___
    -0.63
     feds
    -0.62
     moms
    -0.61
    toggle
    -0.60
    aturdays
    -0.57
     mom
    -0.56
    ¢
    -0.55
     counselors
    -0.54
     canceled
    -0.54
    POSITIVE LOGITS
     util
    1.16
     Whilst
    1.16
     whilst
    1.13
     realise
    1.00
     organised
    0.99
     emphas
    0.97
     recognised
    0.97
     organise
    0.94
     organising
    0.94
     recognise
    0.93
    Act Density 1.986%

    No Known Activations