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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the act of creating or restoring something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viewType
    -0.48
     a
    -0.48
    <eos>
    -0.48
     
    -0.48
     diện
    -0.47
    че
    -0.47
    …
    -0.46
    </strong>
    -0.46
     for
    -0.44
    はじめに
    -0.43
    POSITIVE LOGITS
     myſelf
    1.26
     themſelves
    1.19
     creations
    1.14
     greateſt
    1.12
     Theſe
    1.11
     pleaſure
    1.11
     Jefus
    1.11
     itſelf
    1.11
     Reſ
    1.10
     creation
    1.09
    Act Density 0.106%

    No Known Activations