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

    Neuronpedia

    INDEX
    Explanations

    conversational markers and discourse particles used in casual dialogue

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

    continuation particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     стара
    -0.31
    要
    -0.31
     scolaires
    -0.29
    try
    -0.28
     kebakaran
    -0.26
    ?
    -0.26
     vôtre
    -0.26
     militaires
    -0.26
     seleccionar
    -0.25
    ्ट
    -0.25
    POSITIVE LOGITS
    ことで
    1.71
    することで
    1.30
    事で
    1.23
     ujednoznacz
    1.01
     defaultstate
    1.01
     propOrder
    0.98
    DockStyle
    0.96
    endphp
    0.90
     '\\;'
    0.90
     lenker
    0.88
    Act Density 0.004%

    No Known Activations