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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various grammatical structures

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

    Word "is," "was," or "were" followed by "the," "a," or "an."

    np_acts-logits-general · gemini-2.0-flash

    forms of 'to be' followed by an article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.96
    ⓧ
    -0.90
     يتيمه
    -0.88
    SequentialGroup
    -0.85
     Мексичка
    -0.84
     themſelves
    -0.81
     itſelf
    -0.79
    WithIOException
    -0.79
     raiſ
    -0.78
     fince
    -0.78
    POSITIVE LOGITS
     the
    1.28
     a
    1.05
     an
    0.85
     not
    0.77
     either
    0.75
     called
    0.72
     berupa
    0.70
     actually
    0.70
     comprised
    0.70
     our
    0.66
    Act Density 0.694%

    No Known Activations