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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating welcoming or introductory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    welcometo and start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infór
    -0.56
    gameserver
    -0.50
     Posteriormente
    -0.49
     précédente
    -0.46
    homonymie
    -0.45
     pihaknya
    -0.45
     OkHttpClient
    -0.45
     récentes
    -0.45
     entanto
    -0.44
    ledem
    -0.44
    POSITIVE LOGITS
    Welcome
    0.68
    WELCOME
    0.63
    Willkommen
    0.63
     welcoming
    0.59
     Welcome
    0.59
    welcome
    0.59
     welcome
    0.57
     welcomes
    0.51
     WELCOME
    0.51
     للمعارف
    0.49
    Act Density 0.003%

    No Known Activations