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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts expressed in written form

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and exclamation points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boarded
    -0.70
     pul
    -0.69
     imperson
    -0.69
     elevated
    -0.67
     advanced
    -0.66
     credential
    -0.66
     contested
    -0.66
     expected
    -0.65
     commissioned
    -0.65
     hailed
    -0.65
    POSITIVE LOGITS
     Lastly
    1.83
     Anyway
    1.58
     Finally
    1.53
     ********************************
    1.40
    Anyway
    1.35
    Lastly
    1.34
     Needless
    1.34
     Conversely
    1.33
     Conclusion
    1.32
    Finally
    1.31
    Act Density 0.529%

    No Known Activations