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

    Neuronpedia

    INDEX
    Explanations

    quotations or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EnglishChoose
    -0.79
    تقاوى
    -0.77
    UnsafeEnabled
    -0.71
     nephe
    -0.71
    abestanden
    -0.66
     mergeFrom
    -0.66
     ―――――
    -0.66
     iſt
    -0.65
     propOrder
    -0.65
     itſelf
    -0.65
    POSITIVE LOGITS
    러나
    0.57
     Er
    0.56
     Ho
    0.53
    └──
    0.53
     Ban
    0.50
     …)
    0.49
      (
    0.49
    AGED
    0.49
    おわりに
    0.49
     __('
    0.48
    Act Density 0.195%

    No Known Activations