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

    Neuronpedia

    INDEX
    Explanations

    the auxiliary verb "can" in various contexts

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

    modal verb can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.51
     the
    -0.40
     fellow
    -0.34
    ze
    -0.33
    io
    -0.32
    ī
    -0.32
    __
    -0.32
     __
    -0.32
    tie
    -0.31
     BOY
    -0.31
    POSITIVE LOGITS
     can
    1.44
    Can
    1.18
     canst
    1.15
     Can
    1.12
    can
    1.11
     pouvons
    1.07
     pouvez
    1.07
     può
    1.05
    Puede
    1.01
     puede
    0.98
    Act Density 0.157%

    No Known Activations