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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns mixed with verbs indicating action

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢº
    -0.61
    SAN
    -0.59
    ierre
    -0.59
    worldly
    -0.58
    ':
    -0.56
    airy
    -0.56
    ranch
    -0.54
    ="/
    -0.54
     Subscribe
    -0.53
    ='
    -0.53
    POSITIVE LOGITS
     Lastly
    1.46
    Lastly
    1.19
     Conclusion
    1.08
     Finally
    1.08
    Finally
    1.04
     furthermore
    1.01
    Conclusion
    0.95
    anwhile
    0.91
    Additionally
    0.90
     meanwhile
    0.89
    Act Density 0.757%

    No Known Activations