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

    Neuronpedia

    INDEX
    Explanations

    references to specific technical terms related to equations, formulas, and structured technical content

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Meanwhile
    -0.50
    [
    -0.50
    Meanwhile
    -0.49
                        
    -0.49
    For
    -0.49
     
    -0.48
    And
    -0.48
    <eos>
    -0.46
    1
    -0.46
    2
    -0.46
    POSITIVE LOGITS
     Мексичка
    0.88
    TestingModule
    0.84
    出版年
    0.82
     onAnimation
    0.78
    Jereo
    0.77
    Билгалдахарш
    0.75
     raiſ
    0.75
    ControllerAdvice
    0.75
    addCriterion
    0.73
    =$?
    0.73
    Act Density 0.524%

    No Known Activations