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

    Neuronpedia

    INDEX
    Explanations

    dates or mention of specific events in the format of month-day-year

    oai_token-act-pair · gpt-3.5-turbo

    content related to dates, numbers, and metadata indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bots
    -0.81
     Pascal
    -0.77
     Pupp
    -0.76
     BET
    -0.74
     Julie
    -0.74
     PP
    -0.74
     Kul
    -0.74
     Briggs
    -0.73
     Wil
    -0.72
     Mub
    -0.72
    POSITIVE LOGITS
    12
    1.56
     12
    1.40
    13
    1.30
     13
    1.18
     twelve
    1.08
     1280
    1.07
    11
    1.06
    123
    1.04
    14
    1.01
    122
    1.01
    Act Density 0.158%

    No Known Activations