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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Revenir
    -0.61
     disambiguazione
    -0.59
     geslacht
    -0.56
    ebaran
    -0.55
     ujednoznacz
    -0.54
    limard
    -0.54
    InstrumentedTest
    -0.53
    adhy
    -0.53
     onBackPressed
    -0.52
     GenerationType
    -0.50
    POSITIVE LOGITS
     should
    0.68
     will
    0.65
    should
    0.56
     ought
    0.55
    IsRequired
    0.55
     SHOULD
    0.55
     shouldn
    0.52
     WILL
    0.52
    Shouldn
    0.52
     erwar
    0.51
    Act Density 0.157%

    No Known Activations