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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their associated phrases indicating necessity or obligation

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

    modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.62
    Obfuscated
    -0.56
     autorytatywna
    -0.50
    dafx
    -0.50
     ligiloj
    -0.48
    RegressionTest
    -0.48
    endphp
    -0.45
    Cyfarwyddwr
    -0.45
     ***!
    -0.45
     Administrativna
    -0.45
    POSITIVE LOGITS
     should
    0.63
     be
    0.57
     SHOULD
    0.56
     Should
    0.55
    should
    0.52
     ought
    0.52
     pouvoit
    0.51
     seharusnya
    0.50
     can
    0.50
     deber
    0.48
    Act Density 0.104%

    No Known Activations