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

    Neuronpedia

    INDEX
    Explanations

    the word "to" when preceded by certain verbs or adjectives.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )|^{
    -0.68
     ligation
    -0.65
    nasse
    -0.59
     courants
    -0.56
    banded
    -0.55
    śle
    -0.55
     Arrondissement
    -0.54
    eburger
    -0.53
    Proceed
    -0.53
    fare
    -0.52
    POSITIVE LOGITS
    <bos>
    0.81
     щоб
    0.75
     help
    0.72
    Чтобы
    0.68
     чтобы
    0.68
    เพื่อ
    0.66
     for
    0.65
    InstrumentedTest
    0.65
     để
    0.63
    hasMoreElements
    0.62
    Act Density 1.028%

    No Known Activations