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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that end with a punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     anniversary
    -0.71
    sing
    -0.71
    ibles
    -0.67
    clus
    -0.66
    ãĥĺ
    -0.64
    izons
    -0.64
    bered
    -0.64
    ework
    -0.62
    omet
    -0.62
    stead
    -0.61
    POSITIVE LOGITS
     Anyway
    1.43
     Regardless
    1.17
     Additionally
    1.10
     Furthermore
    1.09
     Nevertheless
    1.09
     Conversely
    1.09
     Therefore
    1.08
     Nonetheless
    1.08
     Similarly
    1.07
     Moreover
    1.06
    Act Density 0.117%

    No Known Activations