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

    Neuronpedia

    INDEX
    Explanations

    dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yesterday
    -0.95
     lately
    -0.91
     tomorrow
    -0.89
     today
    -0.83
    66666666
    -0.81
     earlier
    -0.81
    past
    -0.79
     someday
    -0.78
     ago
    -0.78
    cake
    -0.78
    POSITIVE LOGITS
     anticipation
    0.74
    schild
    0.72
     conjunction
    0.70
    Reviewer
    0.64
     Cologne
    0.64
     spite
    0.62
     Minneapolis
    0.61
     Maiden
    0.60
    osure
    0.60
     Montreal
    0.60
    Act Density 0.220%

    No Known Activations