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

    Neuronpedia

    INDEX
    Explanations

    modal verbs that express intention or conditionality

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

    "Would" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    would like or would be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.65
    يكب
    -0.65
     GeoNames
    -0.60
    TextAppearance
    -0.60
    哋
    -0.58
    Πηγή
    -0.58
     שוליים
    -0.58
     Maguire
    -0.58
    Sonstiges
    -0.56
     Conci
    -0.56
    POSITIVE LOGITS
    Would
    0.97
     WOULD
    0.89
     would
    0.89
     Would
    0.89
    would
    0.86
     likely
    0.86
     normally
    0.82
     rather
    0.79
     ideally
    0.78
    ULD
    0.75
    Act Density 0.185%

    No Known Activations