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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

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

    at that time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.77
     dAtA
    -0.71
     EconPapers
    -0.70
     ویکی‌پدی
    -0.70
    <unused14>
    -0.69
    <unused3>
    -0.69
    <unused17>
    -0.69
    <unused23>
    -0.69
    <unused8>
    -0.69
    [@BOS@]
    -0.69
    POSITIVE LOGITS
    ,
    0.50
     then
    0.48
     (
    0.45
     present
    0.41
      
    0.41
     point
    0.39
     initial
    0.39
     initially
    0.39
    ↵
    0.37
     at
    0.37
    Act Density 0.006%

    No Known Activations