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

    Neuronpedia

    INDEX
    Explanations

    dialogue and interpersonal interactions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Официальный
    -0.58
    DeleteBehavior
    -0.57
    sequelize
    -0.53
     Resolution
    -0.53
     rowspan
    -0.53
     diputados
    -0.52
    complexType
    -0.52
    şört
    -0.51
     publique
    -0.50
     financière
    -0.50
    POSITIVE LOGITS
     chatted
    1.16
     chatting
    1.14
     conversation
    1.04
     chat
    1.00
     chats
    0.93
     chatter
    0.91
     talk
    0.90
     banter
    0.89
     conversational
    0.89
     talking
    0.88
    Act Density 0.209%

    No Known Activations