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

    Neuronpedia

    INDEX
    Explanations

    references to historical publications and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propOrder
    -0.88
     Majefty
    -0.88
    ſelf
    -0.83
    ſelves
    -0.80
     betweenstory
    -0.79
     pleaſure
    -0.79
     itſelf
    -0.78
    expandindo
    -0.77
     faſt
    -0.75
    felves
    -0.75
    POSITIVE LOGITS
     to
    0.33
    뽑
    0.31
    <eos>
    0.29
    ,
    0.29
     stik
    0.29
     […]
    0.28
     [
    0.28
     ar
    0.28
    nameof
    0.27
      
    0.27
    Act Density 0.059%

    No Known Activations