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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ire
    -0.73
    uly
    -0.73
     pit
    -0.71
     ring
    -0.70
     nose
    -0.70
     talent
    -0.70
     deity
    -0.69
    itory
    -0.69
     collar
    -0.69
     hust
    -0.68
    POSITIVE LOGITS
     Additionally
    1.31
     Likewise
    1.26
     Needless
    1.25
     Lastly
    1.25
     Furthermore
    1.24
     However
    1.23
     Conversely
    1.23
     Therefore
    1.22
     Flavoring
    1.22
     Moreover
    1.22
    Act Density 1.176%

    No Known Activations