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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the" and other determiners

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

    the or a followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lámina
    -0.40
     cheminée
    -0.37
     secondaires
    -0.37
     múltiple
    -0.36
     láser
    -0.36
     salvaje
    -0.36
     secundario
    -0.36
     especialidad
    -0.35
     varför
    -0.35
     résine
    -0.35
    POSITIVE LOGITS
    RegressionTest
    0.96
    Vidite
    0.66
    AndEndTag
    0.64
    :✨
    0.60
     חיצוניים
    0.58
     <<<<<<<<<<<<<<
    0.55
    #
    0.54
    ########.
    0.53
    endpush
    0.53
    colgroup
    0.52
    Act Density 0.011%

    No Known Activations