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

    Neuronpedia

    INDEX
    Explanations

    mandatory language in legal or formal documents

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

    usage of the word shall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h3>
    -0.48
     upside
    -0.42
     outside
    -0.42
    Eure
    -0.40
    Pé
    -0.39
    Cari
    -0.39
    backgroundImage
    -0.38
     downside
    -0.38
    ﹣
    -0.37
    Carly
    -0.36
    POSITIVE LOGITS
     shall
    1.93
    shall
    1.73
     Shall
    1.57
     SHALL
    1.55
    Shall
    1.50
     fhall
    1.21
     ſhall
    1.16
     shalt
    1.14
     skall
    1.05
     shal
    0.93
    Act Density 0.009%

    No Known Activations