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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     we
    -0.19
     everyone
    -0.18
     you
    -0.18
     everybody
    -0.17
    irim
    -0.17
    大家
    -0.17
    isse
    -0.16
    人们
    -0.16
     people
    -0.16
    æĪij们
    -0.16
    POSITIVE LOGITS
    è¿Ļæĺ¯
    0.25
    æĿ¥è¯´
    0.23
     personally
    0.20
     ÑįÑĤо
    0.17
     nothing
    0.17
     ÑĨе
    0.16
     NOTHING
    0.16
    whose
    0.15
     Äijó
    0.15
    à¹ģล
    0.15
    Act Density 0.083%

    No Known Activations