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

    Neuronpedia

    INDEX
    Explanations

    occurrences of terms related to chat functionalities

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

    chat or messaging apps

    np_acts-logits-general · gemini-2.0-flash

    chat and messaging notifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.59
     Walkover
    -0.55
    خصة
    -0.52
    HasForeignKey
    -0.51
    FailureListener
    -0.50
    bandcamp
    -0.50
    Scénario
    -0.49
    Weblinks
    -0.47
    patreon
    -0.47
    ArgsConstructor
    -0.46
    POSITIVE LOGITS
     chat
    1.17
     Chat
    1.08
    chat
    1.08
     messaging
    1.04
    Chat
    1.04
     messages
    1.03
     Messages
    1.01
     chats
    0.98
     CHAT
    0.97
     message
    0.96
    Act Density 0.192%

    No Known Activations