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

    Neuronpedia

    INDEX
    Explanations

    verbs or nouns related to having a strong influence or impact

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Announce
    -0.70
     Loading
    -0.70
     Saying
    -0.67
     Quote
    -0.66
     Recap
    -0.65
     Explain
    -0.65
    OOL
    -0.63
     Conclusion
    -0.63
     adds
    -0.60
     opener
    -0.60
    POSITIVE LOGITS
     been
    1.19
     arisen
    1.12
     hitherto
    1.05
     risen
    1.03
     resided
    1.00
    been
    1.00
     helped
    0.98
     sprung
    0.98
     existed
    0.96
     plagued
    0.94
    Act Density 0.169%

    No Known Activations