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

    Neuronpedia

    INDEX
    Explanations

    locations and days of the week mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    incidents or events related to specific locations and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caveat
    -0.65
     mortg
    -0.62
     specificity
    -0.61
     caveats
    -0.61
     Journals
    -0.60
     transcripts
    -0.59
    isphere
    -0.59
     sarc
    -0.59
     throne
    -0.59
     Throne
    -0.59
    POSITIVE LOGITS
     afternoon
    0.91
     injuring
    0.91
     morning
    0.81
     evening
    0.79
     ambush
    0.75
     midday
    0.73
     overnight
    0.73
    andals
    0.73
     night
    0.72
     occ
    0.70
    Act Density 0.313%

    No Known Activations