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

    Neuronpedia

    INDEX
    Explanations

    the repeated use of the word "again"

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

    repeated occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.57
    webElementXpaths
    -0.51
    WriteTagHelper
    -0.47
     transfieras
    -0.47
    RTDA
    -0.46
     informée
    -0.44
    estacks
    -0.43
    craper
    -0.43
     EconPapers
    -0.43
    adaptiveStyles
    -0.41
    POSITIVE LOGITS
     antemano
    0.51
    retudo
    0.50
    onResume
    0.49
     repeatedly
    0.48
    Gön
    0.47
    many
    0.46
     vielfach
    0.46
    xn
    0.46
    epam
    0.45
    TokenNameRPAREN
    0.44
    Act Density 0.003%

    No Known Activations