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

    Neuronpedia

    INDEX
    Explanations

    numerical values and dates within historical contexts

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

    invented in the 20th century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.57
     (
    -0.54
    ↵
    -0.49
      
    -0.49
    ↵↵
    -0.46
    -0.44
     The
    -0.43
    <b>
    -0.42
    (
    -0.40
    _
    -0.40
    POSITIVE LOGITS
     EconPapers
    1.05
    <unused74>
    1.05
    <unused14>
    1.05
    [@BOS@]
    1.04
    <unused43>
    1.04
    <unused28>
    1.04
    <unused42>
    1.04
    <unused41>
    1.04
    <unused16>
    1.04
    <unused23>
    1.04
    Act Density 0.068%
    No Known Activations