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

    Neuronpedia

    INDEX
    Explanations

    interactions and relationships between characters in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untime
    -0.20
    utow
    -0.16
    ieder
    -0.15
    loat
    -0.15
    ilan
    -0.15
    ár
    -0.14
    lÃŃ
    -0.14
    roadcast
    -0.14
    andom
    -0.14
    anche
    -0.14
    POSITIVE LOGITS
     reply
    0.37
     replied
    0.36
     replies
    0.33
    reply
    0.32
     responded
    0.28
     Reply
    0.28
     respond
    0.27
     responds
    0.27
     Replies
    0.27
    Reply
    0.27
    Act Density 0.337%

    No Known Activations