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

    Neuronpedia

    INDEX
    Explanations

    dialogue markers and questioning phrases in conversations

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

    conversational turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lucía
    -0.50
    Tembelea
    -0.49
     énergétique
    -0.49
    irsk
    -0.48
    ärme
    -0.47
    heds
    -0.47
     Italijanski
    -0.46
    uxxxx
    -0.46
     financière
    -0.45
    TypedDataSet
    -0.45
    POSITIVE LOGITS
     AssemblyCompany
    0.65
     AssemblyCulture
    0.43
    writeFieldEnd
    0.34
    ItemBackground
    0.34
    पया
    0.33
     previews
    0.33
    itemBuilder
    0.32
    LabelTagHelper
    0.32
     uParam
    0.32
    MessageOf
    0.31
    Act Density 0.002%

    No Known Activations