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

    Neuronpedia

    INDEX
    Explanations

    language related to live communication and support interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¯
    -0.16
    svp
    -0.15
    ettes
    -0.14
    onation
    -0.14
    resa
    -0.13
    ailles
    -0.13
    gaard
    -0.13
     иÑģполн
    -0.13
    å¡ļ
    -0.13
     Manip
    -0.13
    POSITIVE LOGITS
     chat
    0.55
     Chat
    0.49
    chat
    0.48
    -chat
    0.44
    Chat
    0.44
     chats
    0.44
     chatting
    0.41
     conversation
    0.40
     conversations
    0.38
    èģĬ
    0.38
    Act Density 0.131%

    No Known Activations