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

    Neuronpedia

    INDEX
    Explanations

    sequence markers or indicators of data structure

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

    the beginning of new sections or paragraphs in a document

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

    significantly increased, was paid, was influential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.76
    oredCriteria
    -0.64
    prnewswire
    -0.63
    styleType
    -0.62
    MLLoader
    -0.61
    lée
    -0.61
     sqlalchemy
    -0.60
    KURZBESCHREIBUNG
    -0.60
    govina
    -0.58
     ConstraintSet
    -0.57
    POSITIVE LOGITS
     who
    0.89
     whom
    0.78
    who
    0.70
    whom
    0.68
     estekak
    0.60
    excelente
    0.59
     guiding
    0.57
     personable
    0.54
     namentlich
    0.53
     very
    0.52
    Act Density 0.016%

    No Known Activations