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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.21
    æĪijçļĦ
    -0.15
    ç»ĻæĪij
    -0.15
     saya
    -0.15
    ела
    -0.15
     himself
    -0.15
    ctor
    -0.15
    ä¸Ģ个人
    -0.15
    delegate
    -0.14
    ãģıãĤĮãĤĭ
    -0.14
    POSITIVE LOGITS
     ourselves
    0.37
     talking
    0.23
     all
    0.20
     fortunate
    0.19
     lucky
    0.19
     selves
    0.19
     hearing
    0.18
    eden
    0.18
     witnessing
    0.18
     told
    0.17
    Act Density 0.094%

    No Known Activations