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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or final thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conclusions or summarizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    activated
    -0.83
    cler
    -0.73
    otin
    -0.72
    pes
    -0.72
    drivers
    -0.70
    enta
    -0.69
    href
    -0.67
    opic
    -0.65
     nurs
    -0.64
    apt
    -0.64
    POSITIVE LOGITS
     conclude
    1.05
     concluding
    1.02
     concludes
    0.96
     conclusion
    0.92
     Conclusion
    0.81
    reement
    0.77
     concluded
    0.77
     FANTASY
    0.76
    iary
    0.75
     conclusions
    0.74
    Act Density 0.008%

    No Known Activations