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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks such as periods and exclamation points

    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
     transact
    -0.95
     predec
    -0.93
     displacement
    -0.89
     integ
    -0.88
     consolidation
    -0.88
     contingency
    -0.87
     satell
    -0.87
     policymakers
    -0.87
    ¥ŀ
    -0.87
     refin
    -0.87
    POSITIVE LOGITS
     Seriously
    1.70
     Anyway
    1.56
     Yeah
    1.47
     Yep
    1.43
     ;)
    1.41
    Seriously
    1.41
     Dude
    1.39
     Honestly
    1.38
    Anyway
    1.37
     LOL
    1.34
    Act Density 0.427%

    No Known Activations