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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and assertions related to possibilities or hypothetical scenarios

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

    Auxiliary verbs like "have," "would," or "could"

    np_acts-logits-general · gemini-2.0-flash

    would have / could have + past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.82
    :✨
    -0.81
     nakalista
    -0.81
    IntoConstraints
    -0.79
     &___
    -0.78
     Roskov
    -0.76
     GenerationType
    -0.73
    ScopeManager
    -0.73
    AutoresizingMask
    -0.72
    XmlAccessorType
    -0.72
    POSITIVE LOGITS
     have
    0.78
     hubiera
    0.76
     gewesen
    0.74
     hubiese
    0.73
     hubieran
    0.70
     hätte
    0.69
     had
    0.68
     been
    0.67
     has
    0.67
     đã
    0.66
    Act Density 0.249%

    No Known Activations