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

    Neuronpedia

    INDEX
    Explanations

    instances of people listening and speaking in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lsru
    -0.14
     ÑĢÑĥк
    -0.14
    ź
    -0.13
     thù
    -0.13
    OKIE
    -0.13
     signals
    -0.13
    azo
    -0.13
    -scal
    -0.12
    aders
    -0.12
     подк
    -0.12
    POSITIVE LOGITS
     ram
    0.32
     bab
    0.32
     gab
    0.31
     wax
    0.31
     pont
    0.31
     rant
    0.30
     chatter
    0.30
     discussing
    0.29
     recount
    0.29
     talk
    0.29
    Act Density 0.344%

    No Known Activations