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

    Neuronpedia

    INDEX
    Explanations

    conversations involving statements of acknowledgment and response

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

    actions of speaking and understanding

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

    It detects reported speech and speaker turns in narrative text (places where someone is speaking or the narrator is speaking).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    hilangan
    -0.30
     After
    -0.30
     Ad
    -0.26
     ad
    -0.25
     after
    -0.24
     absence
    -0.24
     message
    -0.23
    ジャー
    -0.23
     Message
    -0.23
     How
    -0.22
    POSITIVE LOGITS
    Personendaten
    0.82
    ंदीखरीदारी
    0.78
     Photocase
    0.74
     utafitiHapana
    0.74
    ロウィン
    0.73
    <unused68>
    0.73
    <unused19>
    0.73
    <unused23>
    0.73
    <unused16>
    0.73
    <unused3>
    0.73
    Act Density 0.522%

    No Known Activations