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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating desire or suggestions

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

    want to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.47
    Ӕ
    -0.43
    UnsafeEnabled
    -0.42
    PROLOG
    -0.42
     protoimpl
    -0.41
    HtmlAttribute
    -0.41
     MenuView
    -0.38
     Wikimedijinoj
    -0.38
    <?
    -0.38
     Yoda
    -0.38
    POSITIVE LOGITS
     fallu
    0.54
     voud
    0.52
     faudrait
    0.52
     vouloir
    0.48
     spørs
    0.47
     faudra
    0.46
     kapturem
    0.45
     querr
    0.44
     quidem
    0.44
     refirió
    0.43
    Act Density 0.061%

    No Known Activations