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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest orders or requests

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

    orders of magnitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.46
    WaitGroup
    -0.44
    QRST
    -0.40
    gehalt
    -0.39
    InputBorder
    -0.37
    bel
    -0.36
    Con
    -0.35
    Tit
    -0.34
     вер
    -0.34
    Class
    -0.34
    POSITIVE LOGITS
     الحره
    0.66
    تقاوى
    0.61
     NSCoder
    0.55
     виправивши
    0.54
     Савезне
    0.54
     يتيمه
    0.54
    expandindo
    0.51
    tagHelperRunner
    0.50
     Infór
    0.49
    parsedMessage
    0.44
    Act Density 0.127%

    No Known Activations