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

    Neuronpedia

    INDEX
    Explanations

    frequent definite articles and proper nouns within text

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

    the word "The"

    np_acts-logits-general · gemini-2.0-flash

    The followed by proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.85
    tvguidetime
    -0.77
     typelib
    -0.77
    GIVEREF
    -0.69
    AddTagHelper
    -0.68
    fastjson
    -0.67
     AssemblyCulture
    -0.66
    /**
    -0.66
     AssemblyVersion
    -0.63
     Мексичка
    -0.62
    POSITIVE LOGITS
     pair
    0.55
    The
    0.49
     []),
    0.48
    daj
    0.48
    pair
    0.48
     trio
    0.46
     duo
    0.46
    Pair
    0.46
    ıyordu
    0.45
    ghan
    0.45
    Act Density 0.286%

    No Known Activations