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

    Neuronpedia

    INDEX
    Explanations

    various types of closing parentheses, brackets, and quotes, indicating the end of expressions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.65
    :
    -0.58
     idéia
    -0.58
     The
    -0.56
    .
    -0.52
    ↵
    -0.51
     !
    -0.51
     At
    -0.49
     :
    -0.49
    !
    -0.48
    POSITIVE LOGITS
     Мексичка
    1.11
     pylint
    1.07
    MigrationBuilder
    1.06
     وتسجيلات
    1.06
    expandindo
    1.03
    ſelf
    0.97
    ſelves
    0.97
    ScopeManager
    0.95
    ValueStyle
    0.93
     ―――――
    0.92
    Act Density 0.177%

    No Known Activations