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

    Neuronpedia

    INDEX
    Explanations

    references to chat features or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -1.09
     disambiguazione
    -0.99
    __':
    -0.89
    withIdentifier
    -0.88
     متعلقه
    -0.82
    MLLoader
    -0.82
     numberWith
    -0.82
    __":
    -0.81
     ModelExpression
    -0.81
    礴
    -0.81
    POSITIVE LOGITS
     chat
    3.41
     Chat
    3.24
    chat
    3.00
    Chat
    2.98
     CHAT
    2.92
     chats
    2.64
    CHAT
    2.53
     chatting
    2.30
     Chats
    2.24
    chats
    2.17
    Act Density 0.034%

    No Known Activations