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

    Neuronpedia

    INDEX
    Explanations

    sentences that end in a period

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks suggesting the completion of thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibur
    -0.82
     dime
    -0.80
     estate
    -0.80
     tier
    -0.76
     reven
    -0.76
     silent
    -0.75
     holiday
    -0.73
    enged
    -0.71
     barric
    -0.71
     hating
    -0.70
    POSITIVE LOGITS
     Researchers
    1.42
     Scientists
    1.28
    Researchers
    1.17
     Moreover
    1.10
     Furthermore
    1.07
    Scientists
    1.06
     PLoS
    1.03
     Although
    1.01
     However
    1.00
     Previous
    0.99
    Act Density 0.399%

    No Known Activations