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

    Neuronpedia

    INDEX
    Explanations

    expressions related to communication and conversation dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imus
    -0.08
    lei
    -0.07
     Livingston
    -0.07
     mat
    -0.06
    rum
    -0.06
     scr
    -0.06
    宿
    -0.06
    roid
    -0.06
    sock
    -0.06
    rium
    -0.06
    POSITIVE LOGITS
     conversation
    0.09
     Conversation
    0.09
    Conversation
    0.08
     topics
    0.08
    conversation
    0.07
     topic
    0.07
    Segue
    0.07
    .topic
    0.07
     steer
    0.07
    /topic
    0.07
    Act Density 0.007%

    No Known Activations