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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    end-of-sentence punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikuman
    -0.68
    itialized
    -0.68
    izoph
    -0.59
     tyr
    -0.58
    ãĥ¼ãĥĨ
    -0.58
     predec
    -0.58
    istically
    -0.57
    imir
    -0.57
     mosqu
    -0.57
    ãĥ¼ãĥĨãĤ£
    -0.56
    POSITIVE LOGITS
     Additionally
    1.05
     Similarly
    1.00
     Moreover
    1.00
     Furthermore
    0.98
     Likewise
    0.97
     Such
    0.96
     Needless
    0.94
     Meanwhile
    0.94
     Conversely
    0.93
     Ultimately
    0.90
    Act Density 1.066%

    No Known Activations