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

    Neuronpedia

    INDEX
    Explanations

    uncommon characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional states or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aud
    -0.78
     orchestr
    -0.76
     swoop
    -0.73
     steroids
    -0.73
     imperson
    -0.70
     hust
    -0.69
     sacked
    -0.68
     plunge
    -0.68
     innocence
    -0.68
     engagement
    -0.68
    POSITIVE LOGITS
    ³³³³³³³³
    1.87
    ³³³³
    1.63
    ³³³³³³³³³³³³³³³³
    1.60
    Posted
    1.56
    Anyway
    1.55
    ³³³
    1.51
    ³³
    1.41
    posted
    1.40
    Anonymous
    1.33
    Conclusion
    1.31
    Act Density 0.334%

    No Known Activations