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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific document referred to as "the memo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    memo or memorandum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.53
    onOptions
    -0.38
     escenario
    -0.36
    IMPORTED
    -0.36
     getUsers
    -0.35
     currentState
    -0.35
    EEEEEEEE
    -0.35
     sainte
    -0.34
    GenerationType
    -0.33
     Friedrich
    -0.33
    POSITIVE LOGITS
     memo
    2.70
     Memo
    2.44
    Memo
    2.28
    memo
    2.23
     MEMO
    1.87
     memorandum
    1.50
     memoranda
    1.39
     Memorandum
    1.26
    メモ
    1.20
     Memor
    1.15
    Act Density 0.010%

    No Known Activations