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

    Neuronpedia

    INDEX
    Explanations

    research findings or scientific studies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate research findings or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pour
    -0.83
    phabet
    -0.70
    estate
    -0.69
    iciary
    -0.68
    ppa
    -0.68
    coe
    -0.68
    ideshow
    -0.68
    icker
    -0.67
    ishers
    -0.66
    iture
    -0.66
    POSITIVE LOGITS
     correlations
    1.05
     correlation
    0.98
     effic
    0.98
     abnormalities
    0.94
     efficacy
    0.90
     causation
    0.85
     anecd
    0.83
     variability
    0.80
     unequivocally
    0.78
     plaus
    0.78
    Act Density 0.194%

    No Known Activations