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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to statistical analysis and measurement in research studies

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

    Numerical values followed by units or symbols

    np_acts-logits-general · gemini-2.0-flash

    values, units, and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -1.00
     idéia
    -0.94
     definately
    -0.92
     piu
    -0.92
     alot
    -0.89
    "....
    -0.85
    ichè
    -0.83
     !"
    -0.78
    ・・・」
    -0.78
     tambien
    -0.78
    POSITIVE LOGITS
     < 
    1.23
     (−
    1.21
     ∼
    1.11
     = 
    1.08
     
    1.05
     × 
    1.02
     + 
    1.01
     (<
    0.97
     ≥
    0.96
     ≤
    0.94
    Act Density 5.711%

    No Known Activations