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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

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

    descriptive adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.96
     zwiſchen
    -0.90
    <unused43>
    -0.90
    <unused28>
    -0.89
    <unused23>
    -0.89
    <unused8>
    -0.89
    <unused14>
    -0.89
    <unused51>
    -0.89
    [@BOS@]
    -0.89
    <pad>
    -0.89
    POSITIVE LOGITS
    ,
    0.42
    ，
    0.33
      
    0.33
     cool
    0.32
     big
    0.32
    、
    0.32
    :
    0.31
    old
    0.31
    "
    0.31
    　
    0.30
    Act Density 0.023%

    No Known Activations