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

    Neuronpedia

    INDEX
    Explanations

    the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tarian
    -0.78
     conservatism
    -0.75
    arily
    -0.71
     planners
    -0.70
     superpower
    -0.67
     currents
    -0.66
     scaling
    -0.65
     cloning
    -0.65
     chained
    -0.65
     drinkers
    -0.64
    POSITIVE LOGITS
     Hence
    1.07
     Amen
    1.01
     Pour
    1.01
     See
    1.00
     Thus
    0.98
     Regist
    0.97
     Whereas
    0.97
     Therefore
    0.97
     Please
    0.95
     Literally
    0.95
    Act Density 0.049%

    No Known Activations