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

    Neuronpedia

    INDEX
    Explanations

    references to chat functionalities and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numberWith
    -0.80
    >>>>>>>>
    -0.77
     &___
    -0.76
     ModelExpression
    -0.76
    /**
    -0.76
    isRequired
    -0.75
    ="">
    -0.74
     disambiguazione
    -0.74
    礴
    -0.73
    ondheim
    -0.73
    POSITIVE LOGITS
     Chat
    1.88
     chat
    1.86
     CHAT
    1.78
    Chat
    1.66
    chat
    1.61
     Chats
    1.53
     chats
    1.53
    CHAT
    1.46
     chatting
    1.38
    ChatColor
    1.33
    Act Density 0.116%

    No Known Activations