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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the indefinite articles "a" and "an" along with prepositions "of" indicating specific relationships or attributes

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

    much of a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.69
     Comprometido
    -0.66
     kasarigan
    -0.64
     aveug
    -0.62
     chrétien
    -0.60
     feroit
    -0.60
     ainfi
    -0.58
     desmotivaciones
    -0.58
     Komunikasi
    -0.57
    étoit
    -0.57
    POSITIVE LOGITS
      
    0.56
     Actual
    0.54
     actual
    0.53
     Rep
    0.52
    ↵↵
    0.52
    (
    0.51
     (
    0.50
     Mats
    0.50
    <eos>
    0.50
     Big
    0.50
    Act Density 0.007%

    No Known Activations