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

    Neuronpedia

    INDEX
    Explanations

    phrases related to initiating and engaging in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äħd
    -0.15
    ItemSelectedListener
    -0.14
    436
    -0.13
    oplayer
    -0.13
    dag
    -0.13
    izyon
    -0.13
    çħ§
    -0.13
    umbotron
    -0.13
     kvin
    -0.13
    avia
    -0.12
    POSITIVE LOGITS
     conversation
    0.75
     discussion
    0.71
     conversations
    0.65
     discussions
    0.62
    conversation
    0.61
    discussion
    0.56
     Conversation
    0.54
     Discussion
    0.52
     discuss
    0.52
     dialogue
    0.52
    Act Density 0.206%

    No Known Activations