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

    Neuronpedia

    INDEX
    Explanations

    content that involves drawing conclusions or summarizing results in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    didSet
    -0.64
    feitura
    -0.62
     Sand
    -0.62
    Véxase
    -0.62
     Ever
    -0.61
    花板
    -0.61
    andu
    -0.60
     Netz
    -0.60
     Ott
    -0.60
    artney
    -0.60
    POSITIVE LOGITS
     conclusions
    1.43
     conclusion
    1.26
     Conclusions
    1.21
     conclude
    1.12
    impulan
    1.10
    conclusion
    1.07
     concludes
    1.00
    结论
    0.99
     Conclusion
    0.99
     conclu
    0.98
    Act Density 0.146%

    No Known Activations