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

    Neuronpedia

    INDEX
    Explanations

    demonstratives indicating proximity or reference to objects or ideas, particularly "this" and "that"

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

    "that" or "this" followed by "is"

    np_acts-logits-general · gemini-2.0-flash

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scolaires
    -0.53
     født
    -0.47
     cittadino
    -0.47
     Ainsi
    -0.46
     Thus
    -0.46
     стоимо
    -0.45
     bianche
    -0.43
    but
    -0.41
    comer
    -0.41
    Thus
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.86
     is
    0.85
     tartalomajánló
    0.80
    }{*}{}
    0.77
    }{*}{
    0.74
    toarele
    0.72
     שוליים
    0.72
    DoubleQuotes
    0.70
     wouldn
    0.69
     will
    0.69
    Act Density 0.208%

    No Known Activations