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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    المكان
    -0.52
     autorytatywna
    -0.48
    CommandType
    -0.43
     Kün
    -0.42
    Insee
    -0.40
     것이
    -0.40
     cherchés
    -0.39
     druck
    -0.38
     Schar
    -0.37
    ọa
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    0.55
    expandindo
    0.55
    exitRule
    0.52
     propOrder
    0.51
    ﹍﹍﹍
    0.50
     OkHttpClient
    0.50
     Mentions
    0.49
    itest
    0.49
    spoiler
    0.49
    PLN
    0.47
    Act Density 0.171%

    No Known Activations