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

    Neuronpedia

    INDEX
    Explanations

    the end of a turn in a conversation or dialogue

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

    technical and general knowledge questions

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects conversation turn boundaries — it activates on the end_of_turn token (end of a user turn).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    OGND
    -0.64
    GEBURTSDATUM
    -0.63
     Administrativna
    -0.61
     المعيارى
    -0.58
    IntoConstraints
    -0.55
    ymce
    -0.50
    SharedCtor
    -0.48
    ьаж
    -0.48
     LIRE
    -0.47
    SharedDtor
    -0.47
    POSITIVE LOGITS
    sizeCache
    0.55
     $_"
    0.49
    ForUser
    0.45
    ientras
    0.45
     Sünde
    0.44
    niſſe
    0.43
    ENEFITS
    0.42
     Füßen
    0.42
     myſelf
    0.42
    PÁG
    0.41
    Act Density 0.127%

    No Known Activations