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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate continuation or addition in a text

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

    "so on"

    np_acts-logits-general · gemini-2.0-flash

    and so on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.67
    DriverManager
    -0.65
    ngdoc
    -0.56
    رشف
    -0.56
     invokingState
    -0.56
    الحياه
    -0.56
    maketitle
    -0.55
    deauna
    -0.55
     Trotzdem
    -0.54
     mergeFrom
    -0.54
    POSITIVE LOGITS
     forth
    1.29
     list
    0.98
     далее
    0.84
     liste
    0.81
     onwards
    0.81
    list
    0.80
     onward
    0.79
     vidare
    0.79
    Forth
    0.78
     Forth
    0.76
    Act Density 0.137%

    No Known Activations