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

    Neuronpedia

    INDEX
    Explanations

    references to memoirs or autobiographies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¦y
    -0.14
    欣
    -0.14
    аниÑĨ
    -0.14
    flater
    -0.14
    arra
    -0.14
    çķĮ
    -0.13
    çĭIJ
    -0.13
    edd
    -0.13
     birthdays
    -0.13
    wed
    -0.13
    POSITIVE LOGITS
     memoir
    0.43
     autobiography
    0.35
     autobi
    0.32
     Memo
    0.31
    memo
    0.30
    Memo
    0.27
     авÑĤ
    0.24
     Aut
    0.23
    aut
    0.23
     auto
    0.23
    Act Density 0.130%

    No Known Activations