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

    Neuronpedia

    INDEX
    Explanations

    information related to specific numbers and statistics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and numerical statistics related to social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.79
    tnc
    -0.77
     dimensional
    -0.76
     complimentary
    -0.76
     compliment
    -0.65
     gentlemen
    -0.65
     bang
    -0.64
     gol
    -0.64
     loaf
    -0.64
     mate
    -0.64
    POSITIVE LOGITS
     Approximately
    1.28
     Nearly
    1.24
     About
    1.12
     Tens
    1.11
     Estimates
    1.11
     Rough
    1.11
    Nearly
    1.09
     Millions
    1.07
     Thousands
    1.06
     Hundreds
    1.06
    Act Density 0.396%

    No Known Activations