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

    Neuronpedia

    INDEX
    Explanations

    references to the New Year

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.14
     raiſ
    -1.06
     avoient
    -1.06
     myſelf
    -1.06
     poffe
    -1.03
     ſever
    -1.03
     faſt
    -1.03
     Majefty
    -1.02
     pleaſure
    -1.02
     pouvoit
    -1.02
    POSITIVE LOGITS
     Richards
    0.65
     Mes
    0.64
     care
    0.62
    ends
    0.61
    ENDS
    0.61
    بوابة
    0.58
     
    0.56
    ADVERTISEMENT
    0.54
     clients
    0.54
    es
    0.53
    Act Density 0.154%

    No Known Activations