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

    Neuronpedia

    INDEX
    Explanations

    phrases or structures indicating procedural requirements or steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.17
     pleaſure
    -1.17
     themſelves
    -1.09
     Majefty
    -1.04
     myſelf
    -1.03
     fevere
    -1.02
     Diſ
    -1.00
     Chriftian
    -0.98
     Chrift
    -0.97
     Monfieur
    -0.97
    POSITIVE LOGITS
     inorder
    1.23
     afin
    1.02
     order
    0.95
    inorder
    0.91
     أجل
    0.82
     Afin
    0.82
    Afin
    0.82
     чтобы
    0.81
    order
    0.79
    为了
    0.77
    Act Density 0.062%

    No Known Activations