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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to conversations and interpersonal communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĿĬ
    -0.15
    ãģĻãģIJ
    -0.14
    bih
    -0.14
    nout
    -0.14
    uger
    -0.14
    á»Ļi
    -0.13
     scr
    -0.13
    баÑĩ
    -0.13
     Equipment
    -0.13
     kiá»ĩn
    -0.13
    POSITIVE LOGITS
     conversation
    0.31
    conversation
    0.24
     Conversation
    0.23
     talk
    0.22
     discussion
    0.22
     topic
    0.21
    versation
    0.20
     conversations
    0.20
    Conversation
    0.20
     topics
    0.19
    Act Density 0.258%

    No Known Activations