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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the word "the" in various contexts

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

    specific nouns after definite article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.59
    OGND
    -0.58
     otomatig
    -0.57
    Hentet
    -0.56
    expandindo
    -0.54
    ArgsConstructor
    -0.54
     kaarangay
    -0.54
    دانشنامهٔ
    -0.53
     дописавши
    -0.52
    Autoritní
    -0.52
    POSITIVE LOGITS
     pauvreté
    0.55
     original
    0.51
     originais
    0.43
     previous
    0.42
     former
    0.42
     usual
    0.41
     oorspron
    0.40
    bibfield
    0.39
     previously
    0.39
    original
    0.39
    Act Density 0.154%

    No Known Activations