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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority figures and decision-making structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.96
     autorytatywna
    -0.94
     للمعارف
    -0.81
    :✨
    -0.79
    AddTagHelper
    -0.77
    tanleria
    -0.73
    GOTREF
    -0.71
     AssemblyCulture
    -0.71
     Chwiliwch
    -0.70
    Rhestr
    -0.68
    POSITIVE LOGITS
    #%%
    0.29
     rest
    0.28
      
    0.27
       
    0.26
    getResources
    0.25
     fate
    0.25
     déclaré
    0.25
     res
    0.24
    те
    0.24
     Fi
    0.24
    Act Density 0.914%

    No Known Activations