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

    Neuronpedia

    INDEX
    Explanations

    specific dates and times mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and times for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     habit
    -0.73
     grop
    -0.70
     wrongly
    -0.70
     lately
    -0.69
     handwriting
    -0.68
     tended
    -0.66
     hated
    -0.66
     misunderstood
    -0.66
     mistakes
    -0.66
     instinctively
    -0.65
    POSITIVE LOGITS
    Tickets
    1.04
     TBD
    1.00
     TBA
    0.94
     Tickets
    0.91
    2020
    0.84
     Launch
    0.82
     2019
    0.80
    Launch
    0.76
     Mondays
    0.72
    aturdays
    0.71
    Act Density 0.423%

    No Known Activations