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

    Neuronpedia

    INDEX
    Explanations

    instances of conversation and social interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     @$_
    -0.15
     actionTypes
    -0.15
    ufen
    -0.15
    onet
    -0.15
    Ã
    -0.15
    olute
    -0.14
    inç
    -0.14
     иÑģполн
    -0.14
    linky
    -0.14
    lems
    -0.13
    POSITIVE LOGITS
     conversation
    0.41
     talk
    0.34
     chat
    0.32
     Conversation
    0.31
    conversation
    0.30
    Conversation
    0.28
     convers
    0.28
     talking
    0.28
     talked
    0.28
     conversations
    0.27
    Act Density 0.280%

    No Known Activations