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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts and usages within the text

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

    as introducing reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſche
    -0.66
     Reſ
    -0.65
     unſ
    -0.64
     ſever
    -0.63
     Inſ
    -0.63
     Houſe
    -0.62
    UrlResolution
    -0.62
     Diſ
    -0.61
    ſelf
    -0.60
     Jefus
    -0.59
    POSITIVE LOGITS
     gdyż
    0.50
     grossen
    0.42
     éste
    0.41
     iż
    0.40
    heureusement
    0.40
     deoarece
    0.40
     malheureusement
    0.40
     parceria
    0.40
    GenerationType
    0.39
     concernés
    0.38
    Act Density 0.062%

    No Known Activations