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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doInBackground
    -0.34
     habr
    -0.33
     promotion
    -0.32
     characters
    -0.31
    characters
    -0.31
     volition
    -0.29
    Het
    -0.29
     Whi
    -0.29
     Characters
    -0.29
    Chham
    -0.29
    POSITIVE LOGITS
    الحياه
    0.73
    RenderAtEndOf
    0.72
     للاسماء
    0.69
    summary
    0.67
    ################
    0.66
    AddTagHelper
    0.60
    المناصب
    0.59
    Халык
    0.57
     dAtA
    0.56
     الحره
    0.55
    Act Density 0.120%

    No Known Activations